prepare for cape

cape_convert.py

@@ -1,14 +1,15 @@
+from glob import glob
 import os
+import tqdm
+import shutil
 import numpy as np
 import plotly.express as ex
 import plotly.graph_objects as go
-from simpleicp import PointCloud, SimpleICP
-from scipy.spatial.distance import cdist
 from custom_utils.custom_utils import _maskFaces
 
 
 
-os.environ["CUDA_VISIBLE_DEVICES"] = '2'
+os.environ["CUDA_VISIBLE_DEVICES"] = '1'
 import tensorflow as tf
 
 gpus = tf.config.experimental.list_physical_devices('GPU')
@@ -24,26 +25,44 @@ if gpus:
         print(e)
 
 from custom_utils.smpl import SMPL
+# from custom_utils.smpl import SMPL
 
 
 folder = '/home/workspace/data/dataset/cape_release'
+# smpl = SMPL(orig_smpl=True)
+
 
 def get_frames():
+    smpl = SMPL(orig_smpl=True)
     # sequences = np.load()
-    test = np.load(os.path.join(folder, 'sequences/03383/shortlong_ATUsquat/shortlong_ATUsquat.000105.npz'))
+    gender_table = np.load('/home/workspace/data/dataset/cape_release/misc/subj_genders.pkl', allow_pickle=True)
+    test = np.load(os.path.join(folder, 'train/male/02474/longshort_ATUsquat/longshort_ATUsquat.000100.npz'))
     faces = np.load(os.path.join(folder, 'misc/smpl_tris.npy'))
-    min_body = np.load(os.path.join(folder, 'minimal_body_shape/03383/03383_minimal.npy')) 
+    min_body = np.load(os.path.join(folder, 'minimal_body_shape/02474/02474_minimal.npy'))
+    shape = np.load(os.path.join(folder, 'minimal_body_shape/02474/betas_2.npy')) 
     offsets_cano = test['v_cano'] - min_body
-    pose = test['pose']
+    pose = test['pose'].astype(np.float32)
-    mask = np.abs(offsets_cano.sum(axis=-1)) < 1e-2
+    shape = np.concatenate((shape, [0] if gender_table['02474'] == 'female' else [1])).astype(np.float32)
+    posed_body = smpl.run(smpl.run_rodrigues(pose[np.newaxis,:]), shape[np.newaxis,:], remove=False)[0].numpy()[0]
+    transl = test['transl']
+    posed_body = posed_body + transl[np.newaxis, :]
+    offset_posed = test['v_posed'] - posed_body
+    mask = np.abs(offsets_cano.sum(axis=-1)) > 1e-2
 
-    smpl = SMPL()
+    zero_body = smpl.run(smpl.run_rodrigues(np.zeros((1, 72), np.float32)), shape[np.newaxis,:], remove=True)[0]
-    smpl.run_garment()
+    zero_body_root, J, _ = smpl.run(smpl.run_rodrigues(np.zeros((1, 72), np.float32)), shape[np.newaxis,:], remove=True)
+    # _, J0, _ = smpl.run(smpl.run_rodrigues(pose[np.newaxis,:]), shape[np.newaxis,:], remove=True, subtract_root=True)
 
-    # verts, faces = _maskFaces(test['v_posed'], faces, mask)
+    posed_body = smpl.run_garment(pose[np.newaxis,:], shape[np.newaxis,:], zero_body)[0].numpy()
+    posed_body_root = smpl.run_garment(pose[np.newaxis,:], shape[np.newaxis,:], zero_body_root)
+    posed_body_root = posed_body_root[0].numpy()
+    # verts, faces = _maskFaces(test['v_cano'], faces, mask)
 
-    x = test['v_cano']
+    # x = test['v_cano']
-    y = min_body
+    # y = min_body
+    x = min_body[smpl.to_keep, :] - J[0,0,:][np.newaxis, :]
+    y = zero_body_root[0].numpy()
+    faces = np.load('custom_utils/smpl_faces_orig.npy')
     fig = go.Figure(data=[
             go.Mesh3d(
                 # 8 vertices of a cube
@@ -171,8 +190,446 @@ def get_frames_pop():
     print()
 
 
+def split_data():
+    from CAPE.data.dataset_configs import dataset_config_dicts
+    count = 0
+    cut_first = 2
+    sample_rate = 1
+
+    src = '/home/workspace/local-data/temp/cape_release/sequences'
+    dst = '/home/workspace/local-data/cape/' + phase + '/' + gender
+    os.makedirs(dst, exist_ok=True)
+
+    config = dataset_config_dicts[gender]
+
+    ids = os.listdir(src)
+
+    for id in ids:
+        if id not in config[phase + '_' + 'subjs']:
+            continue
+
+        garment_dir = os.path.join(src, id)
+        sequences = os.listdir(garment_dir)
+
+        for sequence in sequences:
+            sequence_name = '_'.join(sequence.split('_')[1:])
+            if sequence_name in config['exclude_seqs']:
+                continue
+            if sequence_name not in config[phase + '_' + 'seqs']:
+                continue
+
+            cloth = sequence.split('_')[0]
+            if cloth not in config[phase + '_' + 'cloth']:
+                continue
+
+            if [id, cloth] in config['exclude_cases']:
+                continue
+            
+            frames = sorted(glob(os.path.join(garment_dir, sequence, '*.npz')))
+            if len(frames) == 0:
+                print('{} no files here, skipping ..\n'.format(id+'_'+sequence))
+                return
+            frames = frames[cut_first: -cut_first : sample_rate] # take every k frame
+
+            if len(frames) == 0:
+                continue
+
+            os.makedirs(os.path.join(dst, id, sequence), exist_ok=True)
+            for frame in frames:
+                try:
+                    np.load(frame)
+                except: # skip and report the broken file if any
+                    print('{} broken, skipping..'.format(frame))
+                    continue
+
+                frame_name = frame.split('/')[-1]
+                count += 1               
+                print(id + '_' + frame_name)
+
+                test_name = frame.split('/')
+                test_name.index(id)
+                test_name.index(sequence)
+                test_name.index(frame_name)
+
+                shutil.move(frame, os.path.join(dst, id, sequence, frame_name)) 
+
+    print(count)
+
+
+def verify_split_data():
+    from CAPE.data.dataset_configs import dataset_config_dicts
+    count = 0
+    cut_first = 2
+    sample_rate = 1
+    phase = 'test'
+    gender = 'male'
+    src = '/home/workspace/data/dataset/cape_release/sequences'
+    dst = '/home/workspace/data/dataset/cape_release/' + phase + '/' + gender
+
+    config = dataset_config_dicts[gender]
+
+    ids = os.listdir(src)
+
+    for id in ids:
+        if id not in config[phase + '_' + 'subjs']:
+            continue
+
+        garment_dir = os.path.join(src, id)
+        sequences = os.listdir(garment_dir)
+
+        for sequence in sequences:
+            sequence_name = '_'.join(sequence.split('_')[1:])
+            if sequence_name in config['exclude_seqs']:
+                continue
+            if sequence_name not in config[phase + '_' + 'seqs']:
+                continue
+
+            cloth = sequence.split('_')[0]
+            if cloth not in config[phase + '_' + 'cloth']:
+                continue
+
+            if [id, cloth] in config['exclude_cases']:
+                continue
+            
+            frames = sorted(glob(os.path.join(garment_dir, sequence, '*.npz')))
+            if len(frames) == 0:
+                print('{} no files here, skipping ..\n'.format(id+'_'+sequence))
+                return
+            frames = frames[cut_first: -cut_first : sample_rate] # take every k frame
+
+            if len(frames) == 0:
+                continue
+
+            # os.makedirs(os.path.join(dst, id, sequence), exist_ok=True)
+            for frame in frames:
+                try:
+                    np.load(frame)
+                except: # skip and report the broken file if any
+                    print('{} broken, skipping..'.format(frame))
+                    continue
+
+                frame_name = frame.split('/')[-1]
+                count += 1               
+                print(id + '_' + frame_name)
+
+                # shutil.move(frame, os.path.join(dst, id, sequence, frame_name)) 
+
+    print(count)
+
+
+def merge_pose_shape():
+    src = os.path.join('/home/workspace/local-data/cape', phase, gender)
+    dst = os.path.join('/home/workspace/local-data/cape_processed', phase, gender, 'pose_shape')
+    gender_table = np.load('/home/workspace/local-data/temp/cape_release/misc/subj_genders.pkl', allow_pickle=True)
+    os.makedirs(dst, exist_ok=True)
+
+
+    ids = os.listdir(src)
+
+    for id in ids:
+        garment_dir = os.path.join(src, id)
+        sequences = os.listdir(garment_dir)
+
+        for sequence in sequences:
+            # sequence_name = '_'.join(sequence.split('_')[1:])
+            # cloth = sequence.split('_')[0]
+            
+            frames = sorted(os.listdir(os.path.join(garment_dir, sequence)))
+
+            for frame in frames:
+                frame_name = frame.split('.')
+                assert frame_name[-1] == 'npz', 'It\'s not an npz file!'
+                frame_name = '.'.join(frame_name[:-1])
+
+                output_id = id + '_' + frame_name
+                # continue
+
+                data = np.load(os.path.join(garment_dir, sequence, frame))
+                pose = data['pose']
+                shape = np.load(os.path.join('/home/workspace/data/dataset/cape_release_old/minimal_body_shape', id, 'betas_2.npy'))
+                seq_gender = [0] if gender_table[id] == 'female' else [1]
+                shape = np.concatenate((shape, seq_gender)).astype(np.float32)
+                # body = smpl.run(smpl.run_rodrigues(pose[np.newaxis, :]), shape[np.newaxis,:], remove=False)[0][0]
+                pose_shape = np.concatenate((pose, shape))
+
+                np.save(os.path.join(dst, id + '_' + frame_name + '.npy'), pose_shape)
+
+                print(id + '_' + frame)
+
+
+def create_posed_body():
+    smpl = SMPL(orig_smpl=True)
+    src = os.path.join('/home/workspace/local-data/cape', phase, gender)
+    dst = os.path.join('/home/workspace/local-data/cape_processed', phase, gender, 'mesh_posed_body_no_orient')
+    gender_table = np.load('/home/workspace/data/dataset/cape_release_old/misc/subj_genders.pkl', allow_pickle=True)
+    os.makedirs(dst, exist_ok=True)
+
+    ids = os.listdir(src)
+
+    for id in ids:
+        garment_dir = os.path.join(src, id)
+        sequences = os.listdir(garment_dir)
+
+        for sequence in sequences:
+            # sequence_name = '_'.join(sequence.split('_')[1:])
+            # cloth = sequence.split('_')[0]
+            
+            frames = sorted(os.listdir(os.path.join(garment_dir, sequence)))
+
+            for frame in frames:
+                data = np.load(os.path.join(garment_dir, sequence, frame))
+                pose = data['pose'].astype(np.float32)
+                shape = np.load(os.path.join('/home/workspace/data/dataset/cape_release_old/minimal_body_shape', id, 'betas_2.npy'))
+                seq_gender = [0] if gender_table[id] == 'female' else [1]
+                shape = np.concatenate((shape, seq_gender)).astype(np.float32)
+                # body = smpl.run(smpl.run_rodrigues(pose[np.newaxis, :]), shape[np.newaxis,:], remove=True)[0][0]
+
+                frame_name = frame.split('.')
+                assert frame_name[-1] == 'npz', 'It\'s not an npz file!'
+                frame_name = '.'.join(frame_name[:-1])
+                # np.savez_compressed(os.path.join(dst, id + '_' + frame_name + '.npz'), mesh_body_posed=body)
+
+                pose_2 = pose.copy()
+                pose_2[:3] = 0
+                body_2 = smpl.run(smpl.run_rodrigues(pose_2[np.newaxis, :]), shape[np.newaxis,:], remove=True)[0][0]
+                np.savez_compressed(os.path.join(dst, id + '_' + frame_name + '.npz'), mesh_posed_body_no_orient=body_2)
+                
+
+                print(id + '_' + frame)
+
+
+def create_static():
+    smpl = SMPL(orig_smpl=True)
+    src = os.path.join('/home/workspace/local-data/cape', phase, gender)
+    dst = os.path.join('/home/workspace/local-data/cape_processed', phase, gender, 'mesh_static')
+    src_orig = os.path.join('/home/workspace/local-data/temp/cape_release/sequences')
+    J0 = np.load('custom_data/smpl_root_joint.npy')
+    os.makedirs(dst, exist_ok=True)
+
+    ids = os.listdir(src)
+
+    for id in ids:
+        garment_dir = os.path.join(src, id)
+        sequences = os.listdir(garment_dir)
+
+        for sequence in sequences:
+            # sequence_name = '_'.join(sequence.split('_')[1:])
+            # cloth = sequence.split('_')[0]
+            
+            avaialble_frames = sorted(os.listdir(os.path.join(src_orig, id, sequence)))
+            first_frame = avaialble_frames[0]
+
+            print(first_frame)
+            data = np.load(os.path.join(src_orig, id, sequence, first_frame))
+            frame = data['v_cano'][smpl.to_keep, :] - J0[np.newaxis, :]
+
+            np.savez_compressed(os.path.join(dst, id + '_' + sequence + '.npz'), mesh_static = frame)
+
+            # x = data['v_posed'][smpl.to_keep, :] - J0[np.newaxis, :] - data['transl'][np.newaxis, :]
+            # faces = np.load('custom_utils/smpl_faces_orig.npy')
+            # fig = go.Figure(data=[
+            #         go.Mesh3d(
+            #             # 8 vertices of a cube
+            #             x=x[:,0],
+            #             y=x[:,1],
+            #             z=x[:,2],
+            #             # i, j and k give the vertices of triangles
+            #             i = faces[:,0],
+            #             j = faces[:,1],
+            #             k = faces[:,2]
+            #         ),
+            #     ])
+
+            # fig.update_layout(scene_aspectmode='manual',
+            #                 scene_aspectratio=dict(x=1, y=1, z=1))
+            # fig.update_layout(
+            #     scene = dict(
+            #         xaxis = dict(nticks=4, range=[-1.5,1.5],),
+            #         yaxis = dict(nticks=4, range=[-1.5,1.5],),
+            #         zaxis = dict(nticks=4, range=[-1.5,1.5],),)
+            #         )
+
+            # fig.show()
+
+            # print()
+
+
+
+
+def create_unposed():
+    smpl = SMPL(orig_smpl=True)
+    src = os.path.join('/home/workspace/local-data/cape', phase, gender)
+    dst = os.path.join('/home/workspace/local-data/cape_processed', phase, gender, 'mesh_unposed_no_shape')
+    gender_table = np.load('/home/workspace/data/dataset/cape_release_old/misc/subj_genders.pkl', allow_pickle=True)
+    os.makedirs(dst, exist_ok=True)
+    # faces = np.load('custom_utils/smpl_faces_orig.npy')
+    J0 = np.load('custom_data/smpl_root_joint.npy')
+
+
+    ids = os.listdir(src)
+
+    for id in ids:
+        garment_dir = os.path.join(src, id)
+        sequences = os.listdir(garment_dir)
+
+        for sequence in sequences:
+            # sequence_name = '_'.join(sequence.split('_')[1:])
+            # cloth = sequence.split('_')[0]
+            
+            frames = sorted(os.listdir(os.path.join(garment_dir, sequence)))
+
+            for frame in frames:
+                data = np.load(os.path.join(garment_dir, sequence, frame))
+
+                frame_name = frame.split('.')
+                assert frame_name[-1] == 'npz', 'It\'s not an npz file!'
+                frame_name = '.'.join(frame_name[:-1])
+
+                shape = np.load(os.path.join('/home/workspace/data/dataset/cape_release_old', 'minimal_body_shape/' + id + '/betas_2.npy'))
+                seq_gender = 0 if gender_table[id] == 'female' else 1
+
+                shape_offsets = tf.tensordot(shape[tf.newaxis, :], smpl.shapedirs[seq_gender], axes=[[1], [2]]).numpy()
+                unposed = data['v_cano'][smpl.to_keep, :] - J0[np.newaxis, :] - np.squeeze(shape_offsets)[smpl.to_keep, :]
+
+                np.savez_compressed(os.path.join(dst, id + '_' + frame_name + '.npz'), mesh_unposed_no_shape=unposed)
+
+                # x = unposed
+                # faces = np.load('custom_utils/smpl_faces_orig.npy')
+                # fig = go.Figure(data=[
+                #         go.Mesh3d(
+                #             # 8 vertices of a cube
+                #             x=x[:,0],
+                #             y=x[:,1],
+                #             z=x[:,2],
+                #             # i, j and k give the vertices of triangles
+                #             i = faces[:,0],
+                #             j = faces[:,1],
+                #             k = faces[:,2]
+                #         ),
+                #     ])
+
+                # fig.update_layout(scene_aspectmode='manual',
+                #                 scene_aspectratio=dict(x=1, y=1, z=1))
+                # fig.update_layout(
+                #     scene = dict(
+                #         xaxis = dict(nticks=4, range=[-1.5,1.5],),
+                #         yaxis = dict(nticks=4, range=[-1.5,1.5],),
+                #         zaxis = dict(nticks=4, range=[-1.5,1.5],),)
+                #         )
+
+                # fig.show()
+
+                print(id + '_' + frame)
+
+
+def create_posed():
+    smpl = SMPL(orig_smpl=True)
+    src = os.path.join('/home/workspace/local-data/cape', phase, gender)
+    dst = os.path.join('/home/workspace/local-data/cape_processed', phase, gender, 'mesh_posed')
+    os.makedirs(dst, exist_ok=True)
+    J0 = np.load('custom_data/smpl_root_joint.npy')
+
+
+    ids = os.listdir(src)
+
+    for id in ids:
+        garment_dir = os.path.join(src, id)
+        sequences = os.listdir(garment_dir)
+
+        for sequence in sequences:
+            # sequence_name = '_'.join(sequence.split('_')[1:])
+            # cloth = sequence.split('_')[0]
+            
+            frames = sorted(os.listdir(os.path.join(garment_dir, sequence)))
+
+            for frame in frames:
+                data = np.load(os.path.join(garment_dir, sequence, frame))
+
+                frame_name = frame.split('.')
+                assert frame_name[-1] == 'npz', 'It\'s not an npz file!'
+                frame_name = '.'.join(frame_name[:-1])
+
+                posed = data['v_posed'][smpl.to_keep, :] - J0[np.newaxis, :] - data['transl'][np.newaxis, :]
+
+                np.savez_compressed(os.path.join(dst, id + '_' + frame_name + '.npz'), mesh_posed=posed)
+
+                # x = posed
+                # faces = np.load('custom_utils/smpl_faces_orig.npy')
+                # fig = go.Figure(data=[
+                #         go.Mesh3d(
+                #             # 8 vertices of a cube
+                #             x=x[:,0],
+                #             y=x[:,1],
+                #             z=x[:,2],
+                #             # i, j and k give the vertices of triangles
+                #             i = faces[:,0],
+                #             j = faces[:,1],
+                #             k = faces[:,2]
+                #         ),
+                #     ])
+
+                # fig.update_layout(scene_aspectmode='manual',
+                #                 scene_aspectratio=dict(x=1, y=1, z=1))
+                # fig.update_layout(
+                #     scene = dict(
+                #         xaxis = dict(nticks=4, range=[-1.5,1.5],),
+                #         yaxis = dict(nticks=4, range=[-1.5,1.5],),
+                #         zaxis = dict(nticks=4, range=[-1.5,1.5],),)
+                #         )
+
+                # fig.show()
+
+                print(id + '_' + frame)
+
+
+def create_mask():
+    pass
+
+
+def verify():
+    root = os.path.join('/home/workspace/local-data/cape_processed', phase, gender)
+    
+    mesh_static = os.listdir(os.path.join(root, 'mesh_static'))
+
+    mesh_posed = sorted(os.listdir(os.path.join(root, 'mesh_posed')))
+    mesh_posed_body_no_orient = sorted(os.listdir(os.path.join(root, 'mesh_posed_body_no_orient')))
+    mesh_unposed_no_shape = sorted(os.listdir(os.path.join(root, 'mesh_unposed_no_shape')))
+    pose_shape = sorted(os.listdir(os.path.join(root, 'pose_shape')))
+    mesh_curvature = sorted(os.listdir(os.path.join(root, 'mesh_curvature')))
+
+    mesh_posed = ['.'.join(x.split('.')[:-1]) for x in mesh_posed]
+    mesh_posed_body_no_orient = ['.'.join(x.split('.')[:-1]) for x in mesh_posed_body_no_orient]
+    mesh_unposed_no_shape = ['.'.join(x.split('.')[:-1]) for x in mesh_unposed_no_shape]
+    pose_shape = ['.'.join(x.split('.')[:-1]) for x in pose_shape]
+    mesh_curvature = ['.'.join(x.split('.')[:-1]) for x in mesh_curvature]
+
+    mesh_static = ['.'.join(x.split('.')[:-1]) for x in mesh_static]
+    mesh_posed = ['.'.join(x.split('.')[:-1]) for x in mesh_posed]
+    mesh_posed_body_no_orient = ['.'.join(x.split('.')[:-1]) for x in mesh_posed_body_no_orient]
+    mesh_unposed_no_shape = ['.'.join(x.split('.')[:-1]) for x in mesh_unposed_no_shape]
+    pose_shape = ['.'.join(x.split('.')[:-1]) for x in pose_shape]
+    mesh_curvature = ['.'.join(x.split('.')[:-1]) for x in mesh_curvature]
+
+
+    assert mesh_posed == mesh_posed_body_no_orient == mesh_unposed_no_shape == pose_shape == mesh_curvature
+    assert set(mesh_posed) == set(mesh_posed_body_no_orient) == set(mesh_unposed_no_shape) == set(pose_shape) == set(mesh_static) == set(mesh_curvature)
+
+    pass
+
 
 if __name__ == '__main__':
-    train_split = get_frames()
+    phases = ['test', 'test', 'train', 'train']
+    genders = ['male', 'female', 'male', 'female']
+
+    for phase, gender in zip(phases, genders):
+        # get_frames()
+        # split_data()
+        # verify_split_data()
+        # merge_pose_shape()
+        # create_posed_body()
+        # create_static()
+        # create_unposed()
+        # create_posed()
+        verify()
 
     print()

convert_to_uv_cape.py

@@ -0,0 +1,487 @@
+import os
+import sys
+import tqdm
+import math
+import time
+import random
+import shutil
+import collections
+import argparse
+import threading
+import numpy as np
+import scipy as sp
+import trimesh as tm
+import cmapy as cm
+import scipy.io as sio
+import scipy.interpolate as spi
+import matplotlib.pyplot as plt
+import scipy.stats as stat
+import cv2
+import plotly.express as ex
+import plotly.graph_objects as go
+
+
+from custom_utils.supersmpl_io import readPC2
+
+
+
+os.environ["CUDA_VISIBLE_DEVICES"] = "2"
+
+
+def add_triangle_centers():
+    pass
+
+def dilate(img):
+    uv_mask_2 = img != 0
+    m = img.min()
+    # norm = img.max() - img.min()
+    img  = (img - m) * uv_mask_2 #* (np.invert(uv_mask_2) * -1 + uv_mask_2)
+    size = 1
+    shape = cv2.MORPH_CROSS # cv.MORPH_CROSS cv.MORPH_ELLIPSE MORPH_RECT
+    element = cv2.getStructuringElement(shape, (2 * size + 1, 2 * size + 1), (size, size))
+    result = cv2.dilate(img, element, iterations=1)
+    result = (result + m) * uv_mask
+    return result
+
+def erode(img):
+    # m = img.min()
+    # norm = img.max() - img.min()
+    # img  = (img - m) 
+    size = 1
+    shape = cv2.MORPH_CROSS # cv.MORPH_CROSS cv.MORPH_ELLIPSE MORPH_RECT
+    element = cv2.getStructuringElement(shape, (2 * size + 1, 2 * size + 1), (size, size))
+    result = cv2.erode(img, element, iterations=2)
+    # result = result + m
+    return result
+
+def chunks(lst, n):
+    """Yield successive n-sized chunks from lst."""
+    for i in range(0, len(lst), n):
+        yield lst[i:i + n]
+
+
+class Result():
+    def __init__(self) -> None:
+        self.result = dict()
+
+result_g = Result()
+
+class RBFThread(threading.Thread):
+    def __init__(self, uv_values, id, result):
+        threading.Thread.__init__(self)
+        self.uv_values = uv_values
+        self.id = id
+        self.result = result
+
+    def run(self):
+        print('processing: ' + str(self.id))
+        rbf =  spi.RBFInterpolator(y=uv_map_discreet_unique, d=self.uv_values, neighbors=10)
+        res = rbf(rbf_dest)
+        self.result[self.id] = res
+        pass
+
+def convert_to_uv(res, m2uv, uv_map, verts, neighbours=10, mask=None, method='rbf', garment_uv_mask=None):
+    verts_uv = np.zeros((res * 2, res, 3))
+    uv_values = np.zeros((uv_map.shape[0], 3))
+    uv_values[m2uv[:, 0]] = verts
+    uv_values[m2uv[:, 1]] += verts
+    uv_values = uv_values[uv_map_mask, :] #   add garment mask
+    uv_values /= uv_counter[:, np.newaxis]
+    return_garment_uv_mask = False
+
+    if mask is not None:
+        garment_mask = np.zeros((uv_map.shape[0]), dtype=bool)
+        garment_mask[m2uv[:, 0]] = mask
+        garment_mask[m2uv[:, 1]] += mask
+        garment_mask = garment_mask[uv_map_mask] #   add garment mask
+    else:
+        garment_mask = np.sum(uv_values, axis=-1) != 0
+
+    # test
+    verts_uv[uv_map_discreet_unique[:, 0], uv_map_discreet_unique[:, 1], :] = uv_values
+    # verts_uv_save = verts_uv.copy()
+
+    # garment_mask = np.sum(uv_values, axis=-1) != 0
+    unique_uv_values = uv_values[garment_mask, :]
+    uv_map_discreet_unique_unique = uv_map_discreet_unique[garment_mask, :]
+    rbf_dest_current = rbf_dest
+
+    if garment_uv_mask is None and mask is not None:
+        garment_uv_mask = np.zeros((res * 2, res))
+        garment_uv_mask[uv_map_discreet_unique_unique[:, 0], uv_map_discreet_unique_unique[:, 1]] = 255
+        garment_uv_mask = cv2.morphologyEx(garment_uv_mask, cv2.MORPH_CLOSE, cv2.getStructuringElement(cv2.MORPH_RECT, (4 * 2 + 1, 4 * 2 + 1), (4, 4)), iterations=4)
+        garment_uv_mask_border = garment_uv_mask.astype(bool)
+        garment_uv_mask = cv2.dilate(garment_uv_mask, cv2.getStructuringElement(cv2.MORPH_RECT, (2 * 2 + 1, 2 * 2 + 1), (2, 2)), iterations=2).astype(bool)
+        garment_uv_mask_border = ~garment_uv_mask_border & garment_uv_mask
+        garment_uv_mask = garment_uv_mask * uv_mask[:,:,0]
+        rbf_dest_current = rbf_dest * garment_uv_mask
+        return_garment_uv_mask = True
+
+
+    rbf_dest_current = np.nonzero(rbf_dest_current)
+    rbf_dest_current = np.array(rbf_dest_current).T
+
+    # uv_verts_uniq = np.array(np.nonzero(np.sum(verts_uv, axis=-1))).T
+    if method == 'rbf':
+        interpolator =  spi.RBFInterpolator(y=uv_map_discreet_unique_unique, d=unique_uv_values, neighbors=neighbours, kernel='linear')
+    elif method == 'nearest':
+        interpolator =  spi.NearestNDInterpolator(x=uv_map_discreet_unique_unique, y=unique_uv_values)
+    else:
+        raise NotImplementedError
+
+    final = interpolator(rbf_dest_current)
+
+    result = np.zeros((res * 2, res, 3))
+
+    # not sure, shouldn't be needed
+    # rbf_dest[:, [0,1]] = rbf_dest[:, [1, 0]]
+
+    result[rbf_dest_current[:, 0], rbf_dest_current[:, 1], :] = final
+    result[uv_map_discreet_unique[:, 0], uv_map_discreet_unique[:, 1], :] = uv_values
+    if garment_uv_mask is not None:
+        result = result * garment_uv_mask[:,:,np.newaxis]
+
+    if return_garment_uv_mask:
+        return result, garment_uv_mask, garment_uv_mask_border
+    else:
+        return result 
+
+
+
+def convert_to_uv_batch(res, m2uv, uv_map, verts, neighbours=15, mask=None, method='rbf', garment_uv_mask=None, garment_uv_mask_border=None):
+    batch = verts.shape[0]
+    verts_uv = np.zeros((batch, res * 2, res, 3))
+    uv_values = np.zeros((batch, uv_map.shape[0], 3))
+    uv_values[:, m2uv[:, 0]] = verts
+    uv_values[:, m2uv[:, 1]] += verts
+    uv_values = uv_values[:, uv_map_mask, :]
+    uv_values /= uv_counter[np.newaxis, :, np.newaxis]
+    return_garment_uv_mask = False
+    # test
+    verts_uv[:, uv_map_discreet_unique[:, 0], uv_map_discreet_unique[:, 1], :] = uv_values
+    # verts_uv_save = verts_uv.copy()
+
+    # unique_uv_values_mask = np.sum(uv_values[0, :, :], axis=-1) != 0
+    # unique_uv_values = uv_values[:, unique_uv_values_mask, :]
+    # uv_map_discreet_unique_unique = uv_map_discreet_unique[unique_uv_values_mask, :]
+
+    if mask is not None:
+        garment_mask = np.zeros((uv_map.shape[0]), dtype=bool)
+        garment_mask[m2uv[:, 0]] = mask
+        garment_mask[m2uv[:, 1]] += mask
+        garment_mask = garment_mask[uv_map_mask] #   add garment mask
+    else:
+        garment_mask = np.sum(uv_values[0,:,:], axis=-1) != 0
+
+    unique_uv_values = uv_values[:, garment_mask, :]
+    uv_map_discreet_unique_unique = uv_map_discreet_unique[garment_mask, :]
+    rbf_dest_current = rbf_dest
+
+    # add back mesh vertices that are not part of the garment
+    uv_map_discreet_unique_unique_inv = uv_map_discreet_unique[np.invert(garment_mask), :]
+    rbf_dest_fill = np.zeros((res * 2, res), dtype=bool)
+    rbf_dest_fill[uv_map_discreet_unique_unique_inv[:, 0], uv_map_discreet_unique_unique_inv[:, 1]] = True
+    
+    if garment_uv_mask is None and mask is not None:
+        garment_uv_mask = np.zeros((res * 2, res))
+        garment_uv_mask[uv_map_discreet_unique_unique[:, 0], uv_map_discreet_unique_unique[:, 1]] = 255
+        garment_uv_mask = cv2.morphologyEx(garment_uv_mask, cv2.MORPH_CLOSE, cv2.getStructuringElement(cv2.MORPH_RECT, (2 * 2 + 1, 2 * 2 + 1), (2, 2)), iterations=4)
+        garment_uv_mask = cv2.dilate(garment_uv_mask, cv2.getStructuringElement(cv2.MORPH_RECT, (2 * 2 + 1, 2 * 2 + 1), (2, 2)), iterations=2).astype(bool)
+        return_garment_uv_mask = True
+
+    if garment_uv_mask is not None:
+        rbf_dest_current = (rbf_dest + rbf_dest_fill) * garment_uv_mask + garment_uv_mask_border
+
+    rbf_dest_current = np.nonzero(rbf_dest_current)
+    rbf_dest_current = np.array(rbf_dest_current).T
+
+    # uv_verts_uniq = np.array(np.nonzero(np.sum(verts_uv, axis=-1))).T
+    final = []
+    for i in range(batch):
+        # print('processing frame: ' + str(i))
+        if method == 'rbf':
+            interpolator =  spi.RBFInterpolator(y=uv_map_discreet_unique_unique, d=unique_uv_values[i,:,:], neighbors=neighbours, kernel='linear')
+        elif method == 'nearest':
+            interpolator =  spi.NearestNDInterpolator(x=uv_map_discreet_unique_unique, y=unique_uv_values[i,:,:])
+        else:
+            raise NotImplementedError
+        final.append(interpolator(rbf_dest_current))
+    final = np.asarray(final)
+
+    result = np.zeros((batch, res * 2, res, 3))
+    result[:, rbf_dest_current[:, 0], rbf_dest_current[:, 1], :] = final
+    # result[:, uv_map_discreet_unique[:, 0], uv_map_discreet_unique[:, 1], :] = uv_values
+    result[:, uv_map_discreet_unique_unique[:, 0], uv_map_discreet_unique_unique[:, 1], :] = unique_uv_values
+    if garment_uv_mask is not None:
+        result = result * garment_uv_mask[np.newaxis,:,:,np.newaxis]
+
+    if return_garment_uv_mask:
+        return result, garment_uv_mask
+    else:
+        return result 
+
+def convert_to_uv_batch_label(res, m2uv, uv_map, values, neighbours=15, mask=None, method='rbf', garment_uv_mask=None, garment_uv_mask_border=None):
+    batch = values.shape[0]
+    values = (values + 1) * mask
+    values_uv = np.zeros((batch, res * 2, res))
+    missing = np.zeros((res * 2, res))
+    uv_values = np.zeros((batch, uv_map.shape[0]))
+    uv_values[:, m2uv[:, 0]] = values
+    uv_values[:, m2uv[:, 1]] = values
+    uv_values = uv_values[:, uv_map_mask]
+    return_garment_uv_mask = False
+    # test
+    # verts_uv_save = verts_uv.copy()
+
+    # unique_uv_values_mask = np.sum(uv_values[0, :, :], axis=-1) != 0
+    # unique_uv_values = uv_values[:, unique_uv_values_mask, :]
+    # uv_map_discreet_unique_unique = uv_map_discreet_unique[unique_uv_values_mask, :]
+
+    if mask is not None:
+        garment_mask = np.zeros((uv_map.shape[0]), dtype=bool)
+        garment_mask[m2uv[:, 0]] = mask
+        garment_mask[m2uv[:, 1]] += mask
+        garment_mask = garment_mask[uv_map_mask] #   add garment mask
+    else:
+        raise Exception
+
+    # uv_values = uv_values * garment_mask
+
+    # test 
+    values_uv[:, uv_map_discreet_unique[:, 0], uv_map_discreet_unique[:, 1]] = uv_values
+    missing[uv_map_discreet_unique[:, 0], uv_map_discreet_unique[:, 1]] = (uv_values[0,:] == 0)
+    
+    unique_uv_values = uv_values[:, garment_mask]
+    uv_map_discreet_unique_unique = uv_map_discreet_unique[garment_mask, :]
+    # rbf_dest_current = rbf_dest.astype(bool) + garment_uv_mask_border * uv_mask[:,:,0]
+
+    if garment_uv_mask is None and mask is not None:
+        garment_uv_mask = np.zeros((res * 2, res))
+        garment_uv_mask[uv_map_discreet_unique_unique[:, 0], uv_map_discreet_unique_unique[:, 1]] = 255
+        garment_uv_mask = cv2.morphologyEx(garment_uv_mask, cv2.MORPH_CLOSE, cv2.getStructuringElement(cv2.MORPH_RECT, (2 * 2 + 1, 2 * 2 + 1), (2, 2)), iterations=4)
+        garment_uv_mask = cv2.dilate(garment_uv_mask, cv2.getStructuringElement(cv2.MORPH_RECT, (2 * 2 + 1, 2 * 2 + 1), (2, 2)), iterations=2).astype(bool)
+        return_garment_uv_mask = True
+
+    rbf_dest_current = rbf_dest * garment_uv_mask + missing * garment_uv_mask
+    rbf_dest_current = np.nonzero(rbf_dest_current)
+    rbf_dest_current = np.array(rbf_dest_current).T
+
+    # uv_verts_uniq = np.array(np.nonzero(np.sum(verts_uv, axis=-1))).T
+    final = []
+    for i in range(batch):
+        # print('processing frame: ' + str(i))
+        interpolator =  spi.NearestNDInterpolator(x=uv_map_discreet_unique_unique, y=unique_uv_values[i,:])
+        final.append(interpolator(rbf_dest_current))
+    final = np.asarray(final)
+
+    result = np.zeros((batch, res * 2, res))
+    result[:, uv_map_discreet_unique[:, 0], uv_map_discreet_unique[:, 1]] = uv_values
+    result[:, rbf_dest_current[:, 0], rbf_dest_current[:, 1]] = final
+    if garment_uv_mask is not None:
+        result = result * garment_uv_mask[np.newaxis,:,:]
+
+    if return_garment_uv_mask:
+        return result, garment_uv_mask
+    else:
+        return result 
+
+
+def m2uv_array(m2uv):
+    result = np.zeros((3638, 2), dtype=np.int32)
+    for k, v in m2uv.items():
+        if len(v) == 2:
+            result[k] = list(v)
+        elif len(v) == 1:
+            x = v.pop()
+            result[k] = [x, x]
+        else:
+            assert False
+
+    return result
+
+
+
+def verify_reconstruction(orig, reconstructed):
+    error = np.sqrt(np.sum((orig - reconstructed) ** 2, axis=-1))
+    colors = np.array([cm.color('jet', 1 - i) for i in error])
+    error_sum = np.sum(error)
+
+
+    verts_uv = np.zeros((uv_res * 2, uv_res, 3))
+    uv_values = np.zeros((uv_map.shape[0], 3))
+    uv_values[m2uv[:, 0]] = colors
+    uv_values[m2uv[:, 1]] += colors
+    uv_counter = np.zeros((uv_map.shape[0]))
+    uv_counter[m2uv[:, 0]] = 1
+    uv_counter[m2uv[:, 1]] += 1
+    uv_values /= uv_counter[:, np.newaxis]
+    verts_uv[uv_map_discreet[:, 0], uv_map_discreet[:, 1], :] = uv_values
+    fig = plt.figure(figsize=(15, 15))
+    ax = fig.add_subplot(111)
+    ax.scatter(uv_map[:, 0], uv_map[:, 1], s=5, c=uv_values/255)
+    plt.show()
+
+
+
+    fig = plt.figure(figsize=(15, 15))
+    ax = fig.add_subplot(121, projection='3d')
+    x = orig
+    ax.set_xlim3d(-1, 1)
+    ax.set_ylim3d(-1, 1)
+    ax.set_zlim3d(-1, 1)
+    ax.set_xlabel("X")
+    ax.set_ylabel("Y")
+    ax.set_zlabel("Z")
+    ax.scatter(x[:, 0], x[:, 1], x[:, 2], s=5)
+
+    ax = fig.add_subplot(122, projection='3d')
+    x = reconstructed#[error > 0.1, :]
+    ax.set_xlim3d(-1, 1)
+    ax.set_ylim3d(-1, 1)
+    ax.set_zlim3d(-1, 1)
+    ax.set_xlabel("X")
+    ax.set_ylabel("Y")
+    ax.set_zlabel("Z")
+    ax.scatter(x[:, 0], x[:, 1], x[:, 2], s=5, c=colors/255) #[error > 0.1, :]
+
+    plt.show()
+
+    pass
+
+# https://stackoverflow.com/questions/38187286/find-unique-pairs-in-list-of-pairs
+def unique_pairs(a):
+    a.sort(axis=1)
+    b = np.ascontiguousarray(a).view(
+        np.dtype((np.void, a.dtype.itemsize * a.shape[1]))
+    )
+    _, inv, ct = np.unique(b, return_inverse=True, return_counts=True)
+    return ct[inv] == 1
+
+
+def unique_uv_map_mask(uv_map_discreet):
+    mask = np.zeros((uv_map_discreet.shape[0]), dtype=bool)
+    temp = np.zeros((uv_res * 2, uv_res))
+    for p in uv_map_discreet:
+        temp[p[0], p[1]] += 1
+    # temp = temp == 1
+    for i, p in enumerate(uv_map_discreet):
+        if temp[p[0], p[1]] == 1:
+            mask[i] = True
+        elif temp[p[0], p[1]] == 2:
+            mask[i] = True
+            temp[p[0], p[1]] = 0
+    return mask
+
+
+def test(verts, faces, values):
+    uv_values = np.zeros((uv_map.shape[0], 3))
+    uv_values[m2uv[:, 0]] = values
+    uv_values[m2uv[:, 1]] += values
+    uv_counter = np.zeros((uv_map.shape[0]))
+    uv_counter[m2uv[:, 0]] = 1
+    uv_counter[m2uv[:, 1]] += 1
+    uv_values /= uv_counter[:, np.newaxis]
+    x = uv_values
+    verts = np.concatenate((verts, np.zeros((15068, 1))), axis=-1)
+    im = ((x - x.min()) / (x.max() - x.min())) * 255
+    tm.Trimesh(verts, faces, vertex_colors=im.astype(np.int32)).show()
+
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument("-f", "--folder", help = "end of range", default='/home/workspace/data/dataset/cape_processed/train/male')
+    parser.add_argument("-s", "--start", help = "start of range", default=0)
+    parser.add_argument("-e", "--end", help = "end of range", default=100)
+    parser.add_argument("-n", "--name", help = "end of range", default='lhunor')
+    args = parser.parse_args()
+
+    # smpl = SMPL('FeatureLines/superSMPL')
+
+
+    F = np.load("custom_utils/smpl_faces_orig.npy")
+    folder = args.folder
+    uv_map = np.load('custom_utils/stretched_uv_map_3_orig.npy')
+    m2uv = np.load('custom_utils/m2uv_orig.npy', allow_pickle=True).item()
+    m2uv = m2uv_array(m2uv)
+    uv_mask = np.load('custom_utils/mask_256x512.npy')
+    curvature_label_type = '6_25'
+
+    uv_res = 256
+    uv_mask = (cv2.resize(uv_mask * 255.0, (uv_res, uv_res * 2)) / 255).astype(bool)[:, :, np.newaxis]
+    # uv_mask_dilate = cv2.erode(uv_mask.astype(np.float32), cv2.getStructuringElement(cv2.MORPH_CROSS, (2 * 2 + 1, 2 * 2 + 1), (2, 2)), iterations=1).astype(bool)[:, :, np.newaxis]
+    # uv_mask_border = uv_mask * np.invert(uv_mask_dilate)
+    uv_mask = cv2.dilate(uv_mask.astype(np.float32), cv2.getStructuringElement(cv2.MORPH_RECT, (2 * 2 + 1, 2 * 2 + 1), (2, 2)), iterations=2).astype(bool)[:, :, np.newaxis]
+
+    uv_map_discreet = np.floor(uv_map * uv_res).astype(np.int32)
+    uv_map_mask = unique_uv_map_mask(uv_map_discreet)
+
+    uv_counter = np.zeros((uv_map.shape[0]))
+    uv_counter[m2uv[:, 0]] = 1
+    uv_counter[m2uv[:, 1]] += 1
+    uv_counter = uv_counter[uv_map_mask]
+
+    uv_map_discreet_unique = uv_map_discreet[uv_map_mask, :]
+
+    rbf_dest = np.ones((uv_res * 2, uv_res))
+    rbf_dest[uv_map_discreet_unique[:, 0], uv_map_discreet_unique[:, 1]] = 0
+    rbf_dest[np.invert(uv_mask[:,:,0])] = 0
+    # rbf_dest = np.nonzero(rbf_dest)
+    # rbf_dest = np.array(rbf_dest).T
+    # rbf_dest[:, [0,1]] = rbf_dest[:, [1, 0]]
+    # rbf_dest = rbf_dest[unique_pairs(rbf_dest), :] # not good, unique_pairs doesn't consider coord order
+
+
+    # os.makedirs(os.path.join(folder, 'uv_posed_body_no_orient'), exist_ok=True)
+    # os.makedirs(os.path.join(folder, 'uv_posed'), exist_ok=True)
+    # os.makedirs(os.path.join(folder, 'uv_curvature'), exist_ok=True)
+    # os.makedirs(os.path.join(folder, 'uv_unposed_no_shape'), exist_ok=True)
+    # # os.makedirs(os.path.join(folder, 'uv_mask'), exist_ok=True)
+    # os.makedirs(os.path.join(folder, 'uv_static'), exist_ok=True)
+
+    frames = os.listdir(os.path.join(folder, 'pose_shape'))[int(args.start):int(args.end)]
+
+    for frame in tqdm.tqdm(frames):
+        frame_name = frame.split('.')
+        frame_name = '.'.join(frame_name[:-1])
+        static_frame_name = frame_name.split('.')[0]
+
+        verts_static = np.load(os.path.join(folder, 'mesh_static', static_frame_name + '.npz')); verts_static = verts_static['mesh_static']
+        mask = np.ones((3638), bool)
+        body_no_orient = np.load(os.path.join(folder, 'mesh_posed_body_no_orient', frame_name + '.npz')); body_no_orient = body_no_orient['mesh_posed_body_no_orient']
+        gt = np.load(os.path.join(folder, 'mesh_posed', frame_name + '.npz')); gt = gt['mesh_posed']
+        curvature = np.load(os.path.join(folder, 'mesh_curvature', frame_name + '.npz')); curvature = curvature['mesh_curvature']
+        mesh_unposed_no_shape = np.load(os.path.join(folder, 'mesh_unposed_no_shape', frame_name + '.npz')); mesh_unposed_no_shape = mesh_unposed_no_shape['mesh_unposed_no_shape']
+
+        body_no_orient, gt, curvature, mesh_unposed_no_shape = body_no_orient[np.newaxis,:,:], gt[np.newaxis,:,:], curvature[np.newaxis,:], mesh_unposed_no_shape[np.newaxis,:,:]
+
+        # start = time.perf_counter()
+
+
+        uv_verts_static, garment_uv_mask, garment_uv_mask_border = convert_to_uv(uv_res, m2uv, uv_map, verts_static, neighbours=3, mask=mask, method='rbf', garment_uv_mask=None)
+        uv_verts_static = uv_verts_static.astype(np.float32)
+        # uv_body_static = convert_to_uv(uv_res, m2uv, uv_map, body_static, neighbours=3, mask=None, method='rbf', garment_uv_mask=None).astype(np.float32)
+        uv_posed_body_no_orient = convert_to_uv_batch(uv_res, m2uv, uv_map, body_no_orient[:, :, :], neighbours=3, mask=None, method='rbf', garment_uv_mask=None, garment_uv_mask_border=garment_uv_mask_border).astype(np.float32)
+        uv_gt = convert_to_uv_batch(uv_res, m2uv, uv_map, gt[:, :, :], neighbours=3, mask=mask, method='rbf', garment_uv_mask=garment_uv_mask, garment_uv_mask_border=garment_uv_mask_border).astype(np.float32)
+        uv_curvature = convert_to_uv_batch_label(uv_res, m2uv, uv_map, curvature[:, :], neighbours=3, mask=mask, method='nearest', garment_uv_mask=garment_uv_mask, garment_uv_mask_border=garment_uv_mask_border).astype(np.float32)
+        uv_unposed_no_shape = convert_to_uv_batch(uv_res, m2uv, uv_map, mesh_unposed_no_shape[:, :, :], neighbours=3, mask=mask, method='rbf', garment_uv_mask=garment_uv_mask, garment_uv_mask_border=garment_uv_mask_border).astype(np.float32)
+        # print(time.perf_counter() - start)
+
+        uv_posed_body_no_orient, uv_gt, uv_curvature, uv_unposed_no_shape = uv_posed_body_no_orient[0], uv_gt[0], uv_curvature[0], uv_unposed_no_shape[0]
+
+        # start = time.perf_counter()
+        if not os.path.exists(os.path.join(folder, 'uv_static', static_frame_name + '.npz')):
+            np.savez_compressed(os.path.join(folder, 'uv_static', static_frame_name + '.npz'), uv_static=uv_verts_static)
+            # np.save(os.path.join(folder, id, 'body_static_uv.npy'), uv_body_static)
+            # np.savez_compressed(os.path.join(folder, 'uv_mask', static_frame_name + '.npz'), uv_mask=garment_uv_mask)
+
+        np.savez_compressed(os.path.join(folder, 'uv_posed_body_no_orient', frame_name + '.npz'), uv_posed_body_no_orient=uv_posed_body_no_orient)
+        np.savez_compressed(os.path.join(folder, 'uv_posed', frame_name + '.npz'), uv_gt=uv_gt)
+        np.savez_compressed(os.path.join(folder, 'uv_curvature', frame_name + '.npz'), curvature_uv=uv_curvature)
+        np.savez_compressed(os.path.join(folder, 'uv_unposed_no_shape', frame_name + '.npz'), uv_unposed_no_shape=uv_unposed_no_shape)
+
+
+        # print(time.perf_counter() - start)
+        
+        pass
+

curvature_labels_cape.py

@@ -0,0 +1,271 @@
+import os
+import sys
+import tqdm
+import argparse
+import random
+import string
+import numpy as np
+import trimesh as tm
+import cmapy as cm
+import scipy as sp
+import scipy.io as sio
+import plotly.graph_objects as go
+from pyntcloud import PyntCloud
+from scipy.sparse import csr_matrix, coo_matrix
+from scipy.sparse.csgraph import floyd_warshall, dijkstra
+
+from custom_utils.supersmpl_io import readPC2, readPC2Frame, writePC2, readOBJ
+from custom_utils.custom_utils import _maskFaces
+# from FeatureLines.superSMPL.smpl import SMPL
+
+os.environ["CUDA_VISIBLE_DEVICES"] = "1"
+import tensorflow as tf
+gpus = tf.config.experimental.list_physical_devices('GPU')
+if gpus:
+    try:
+        for gpu in gpus:
+            tf.config.experimental.set_memory_growth(gpu, True)
+
+    except RuntimeError as e:
+        print(e)
+from custom_utils.smpl import SMPL
+
+smpl = SMPL(orig_smpl=True)
+
+
+def get_skirt_body():
+    body = readOBJ('FeatureLines/superSMPL_skirt.obj')
+
+    return body[0]
+
+
+def export_to_ply(mesh, file):
+    ply = tm.exchange.ply.export_ply(mesh, encoding='binary', vertex_normal=True, include_attributes=True)
+    output_file = open(file, "wb+")
+    output_file.write(ply)
+    output_file.close()
+
+
+def get_closest_n_points(verts, idx, n):
+    dist = sp.spatial.distance.cdist(verts[idx, :], verts)
+    dist[dist == 0] = 1e9
+    idx_sort = np.argsort(dist, axis=-1)
+    closest = idx_sort[:, :n]
+    return closest
+
+
+def histedges_equalN(x, nbin):
+    npt = len(x)
+    return np.interp(np.linspace(0, npt, nbin + 1),
+                     np.arange(npt),
+                     np.sort(x))
+
+
+
+def k_neighbours(k):
+    body = get_skirt_body()
+    adj = np.ones((14475, 14475)) * 9999 # ???
+    diagonal = np.linspace(0, 14474, 14475, dtype=np.int32)
+    m = tm.Trimesh(body, F, process=False, validate=False)
+    edges = m.edges_unique
+    lengths = m.edges_unique_length
+    adj[edges[:, 0], edges[:, 1]] = lengths
+    adj[edges[:, 1], edges[:, 0]] = lengths
+    adj[diagonal, diagonal] = 0
+
+    adj = csr_matrix(adj)
+    dist = dijkstra(adj, directed=False, unweighted=False, limit=0.5)
+
+    np.save('MeshUtils/dijkstra_skirt.npy', dist)
+
+    # dist = floydWarshall(adj, 14475)
+
+    # idx_sort = np.argsort(dist, axis=-1)
+    # closest = idx_sort[:, :k]
+
+    pass
+
+
+def generate_curvatures(folder, neighbourhood, save_folder):
+    ids = os.listdir(folder)[int(args.start):int(args.end)]
+    # gender_table = np.load('/home/workspace/data/dataset/cape_release/misc/subj_genders.pkl', allow_pickle=True)
+    faces = np.load('custom_utils/smpl_faces_orig.npy')
+    k_neighbors = np.load('custom_data/dijkstra_orig_argsort_25.npy')
+
+    os.makedirs(os.path.join(save_folder, 'curvatures_raw'), exist_ok=True)
+
+    for id in tqdm.tqdm(ids):
+        garment_dir = os.path.join(folder, id)
+
+        sequences = os.listdir(garment_dir)
+
+        for sequence in sequences:
+            frames = os.listdir(os.path.join(garment_dir, sequence))
+
+            for frame in frames:
+                data = np.load(os.path.join(folder, id, sequence, frame))
+                # pose = data['poses']
+                # shape = np.load(os.path.join('/home/workspace/data/dataset/cape_release/minimal_body_shape', id, id + '_minimal.npy'))
+                # gender = [0] if gender_table[id] == 'female' else [1]
+                # shape = np.concatenate((shape, gender)).astype(np.float32)
+                # body = smpl.run(smpl.run_rodrigues(pose[np.newaxis, :]), shape[np.newaxis,:], remove=False)[0][0]
+
+                verts = data['v_posed'][smpl.to_keep, :]
+
+                m = tm.Trimesh(verts, faces, process=False, validate=False)
+                export_to_ply(m, temp_file)
+
+                cloud = PyntCloud.from_file(temp_file)
+                # cloud.plot(mesh=True)
+
+                ev = cloud.add_scalar_field("eigen_values", k_neighbors=k_neighbors)
+                cloud.add_scalar_field("curvature", ev=ev)
+                curvature = np.array(cloud.points["curvature(" + str(neighbourhood+1) + ")"])
+
+                frame_name = frame.split('.')
+                assert frame_name[-1] == 'npz', 'It\'s not an npz file!'
+                frame_name = '.'.join(frame_name[:-1])
+
+                np.save(os.path.join(save_folder, 'curvatures_raw', id + '_' + frame_name + '.npy'), np.array(curvature))
+                
+                print(id + '_' + frame)
+
+
+def get_bins(values, nr_of_bins):
+    flattened = []
+    for c in values:
+        flattened.extend(c.flatten())
+    flattened = np.array(flattened)
+    bins = histedges_equalN(flattened, nr_of_bins)
+    return bins
+
+
+def generate_curvature_labels(folder, bins):
+    os.makedirs(os.path.join(save_folder, 'mesh_curvature'), exist_ok=True)
+
+    frames = os.listdir(folder)#[int(args.start):int(args.end)]
+    labels = np.linspace(0, bins.shape[0] - 2, bins.shape[0] - 1)
+
+
+    for frame in tqdm.tqdm(frames):
+        curvature = np.load(os.path.join(folder, frame))
+        frame_labels = np.zeros((curvature.shape[0]), dtype=np.float32)
+        for j in range(bins.shape[0] - 2):
+            frame_labels[(curvature >= bins[j]) * (curvature < bins[j+1])] = labels[j]
+        frame_labels[curvature >= bins[-2]] = labels[-1]
+    
+        frame_name = frame.split('.')
+        assert frame_name[-1] == 'npy', 'It\'s not an npy file!'
+        frame_name = '.'.join(frame_name[:-1])
+        np.savez_compressed(os.path.join(save_folder, 'mesh_curvature', frame_name + '.npz'), mesh_curvature=frame_labels)
+
+    # ids = os.listdir(folder)#[:10]
+    # labels = np.linspace(0, bins.shape[0] - 2, bins.shape[0] - 1)
+
+    # i = 0
+    # for id in tqdm.tqdm(ids):
+    #     garment_dir = os.path.join(folder, id)
+
+
+    #     curvature = curvatures[i]
+    #     i += 1
+
+    #     curvature_label = np.zeros((curvature.shape[0], curvature.shape[1]))
+    #     frame = 0
+    #     for frame in range(curvature.shape[0]):
+    #         frame_labels = np.zeros((curvature.shape[1]), dtype=np.float32)
+    #         for j in range(bins.shape[0] - 2):
+    #             frame_labels[(curvature[frame, :] >= bins[j]) * (curvature[frame, :] < bins[j+1])] = labels[j]
+    #         frame_labels[curvature[frame, :] >= bins[-2]] = labels[-1]
+    #         curvature_label[frame, :] = frame_labels
+    #         frame += 1
+
+    #     unmasked_label = np.zeros((curvature.shape[0], 14475), dtype=np.float32)
+    #     unmasked_label[:, mask] = curvature_label
+    #     np.save(os.path.join(garment_dir, "curvature_label_" + str(nr_of_labels) + "_" + str(neighbourhood) + ".npy"), unmasked_label)
+        # writePC2(os.path.join(garment_dir, "curvature_label_" + str(nr_of_labels) + "_" + str(neighbourhood) + ".pc16"), unmasked_label, True)
+
+
+def visualize_curvature_labels(folder):
+    frames = os.listdir(os.path.join(folder, 'mesh_curvature'))#[:10]
+    faces = np.load('custom_utils/smpl_faces_orig.npy')
+
+    for _ in range(10):
+    
+        frame = random.choice(frames)
+        mesh_posed = np.load(os.path.join(folder, 'mesh_posed', frame)); mesh_posed = mesh_posed['mesh_posed']
+        mesh_curvature = np.load(os.path.join(folder, 'mesh_curvature', frame)); mesh_curvature = mesh_curvature['mesh_curvature']
+
+        colors = np.array([cm.color('jet', 1 - i) for i in np.linspace(0, 1, int(mesh_curvature.max()+1))])
+        colors_binned = np.zeros((mesh_curvature.shape[0], 3))
+        for i in range(int(mesh_curvature.max())+1):
+            print(np.count_nonzero(mesh_curvature == i))
+            colors_binned[mesh_curvature == i, :] = colors[i]
+
+        x = mesh_posed
+        meshes = [go.Mesh3d(
+                    x=x[:,0],
+                    y=x[:,2],
+                    z=x[:,1],
+                    i = faces[:,0],
+                    j = faces[:,1],
+                    k = faces[:,2],
+                    vertexcolor=colors_binned
+                    ),]
+
+        fig = go.Figure(data=meshes)
+        fig.update_layout(scene_aspectmode='manual', scene_aspectratio=dict(x=1, y=1, z=1))
+        fig.update_layout(
+            scene = dict(
+                xaxis = dict(nticks=4, range=[-1.5,1.5],),
+                yaxis = dict(nticks=4, range=[-1.5,1.5],),
+                zaxis = dict(nticks=4, range=[-1.5,1.5],),)
+                )
+
+        fig.show()
+
+        print()
+
+
+def read_raw_curvatures(folder):
+
+    frames = os.listdir(folder)#[int(args.start):int(args.end)]
+
+    curvatures_all = []
+
+    for frame in tqdm.tqdm(frames):
+        curv = np.load(os.path.join(folder, frame))
+        curvatures_all.append(curv)
+    
+    return curvatures_all
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument("-if", "--in_folder", help = "process the given folder", default=r'/home/workspace/local-data/cape_processed/test/male/curvatures_raw')
+    parser.add_argument("-of", "--out_folder", help = "process the given folder", default=r'/home/workspace/local-data/cape_processed/test/male')
+    parser.add_argument("-s", "--start", help = "start of range", default=0)
+    parser.add_argument("-e", "--end", help = "end of range", default=1500)
+    parser.add_argument("-n", "--name", help = "end of range", default="lhunor")
+    args = parser.parse_args()
+
+    F = np.load("custom_utils/smpl_faces_orig.npy")
+    # k_neighbours(k=25)
+
+    folder = args.in_folder
+    save_folder = args.out_folder #'/home/workspace/data/dataset/cape_processed'
+    nr_of_labels = 6
+    neighbourhood = 25
+    temp_file = '/home/workspace/local-data/temp/' + ''.join(random.choice(string.ascii_lowercase) for i in range(10)) + '.ply'
+    # dist = np.load('custom_data/dijkstra.npy')
+    # dist = np.load('MeshUtils/dijkstra_skirt.npy')
+
+    # generate_curvatures(folder, neighbourhood, save_folder)
+    # curvatures = read_raw_curvatures(folder)
+    # bins = get_bins(curvatures, nr_of_labels)
+    # np.save('custom_data/cape_2_train_male_bins.npy', bins)
+    bins = np.load('custom_data/cape_2_train_male_bins.npy')
+    generate_curvature_labels(folder, bins)
+    # visualize_curvature_labels(save_folder)
+
+    pass

dataset.py

@@ -54,7 +54,7 @@ from custom_utils.custom_utils import nest_conditions, batch_to_dict
 
 
 class StaticDataset():
-    def __init__(self, folder, signature, use_filled=False, resolutions=[512], in_memory=True) -> None:
+    def __init__(self, folder, signature, use_filled=False, resolutions=[512], in_memory=True, is_cape=False) -> None:
         self.store = dict()
         self.signature = signature
         self.folder = folder
@@ -68,9 +68,20 @@ class StaticDataset():
             self.keys.append('uv_static_128')
         self.resolutions = resolutions
         self.filled = ''
+        self.is_cape = is_cape
         if use_filled:
             self.filled = '_filled'
 
+        if is_cape:
+            self.uv_masks = dict()
+            uv_mask = np.load('custom_data/garment_uv_mask_full.npy').astype(np.int32)
+            self.uv_masks[512] = uv_mask.astype(np.float32)
+            for res in [32, 64, 128, 256]:
+                down = tf.image.resize(uv_mask[:,:,tf.newaxis], size=(res, int(res/2)), method=tf.image.ResizeMethod.NEAREST_NEIGHBOR)
+                down = np.squeeze(down.numpy().astype(np.float32))
+                self.uv_masks[res] = down
+
+
 
     def read(self, id):
         data = dict()
@@ -83,12 +94,18 @@ class StaticDataset():
             if 'uv_static' + res_string in self.signature.keys():
                 uv_static = np.load(os.path.join(self.folder, 'uv_static' + self.filled + res_string, id +  '.npz')); uv_static = uv_static['uv_static' + self.filled]; data['uv_static' + res_string] = uv_static
             if 'uv_mask' + res_string in self.signature.keys():
+                if self.is_cape:
+                    data['uv_mask' + res_string] = self.uv_masks[res]
+                else:
                     uv_mask = np.load(os.path.join(self.folder, 'uv_mask' + res_string, id + '.npz')); uv_mask=uv_mask['uv_mask']; uv_mask = uv_mask.astype(np.float32); data['uv_mask' + res_string] = uv_mask
 
 
         if 'mesh_static' in self.signature.keys():
-            mesh_static = np.load(os.path.join(self.folder, 'mesh_static', id +  '.npz')); mesh_static = mesh_static['mesh_static']; data['mesh_static'] = mesh_static
+            mesh_static = np.load(os.path.join(self.folder, 'mesh_static', id +  '.npz')); mesh_static = mesh_static['mesh_static']; data['mesh_static'] = mesh_static.astype(np.float32)
         if 'mesh_mask' in self.signature.keys():
+            if self.is_cape:
+                data['mesh_mask'] = np.ones((3638), np.float32)
+            else:
                 mesh_mask = np.load(os.path.join(self.folder, 'mesh_mask', id + '.npy')); mesh_mask = mesh_mask.astype(np.float32); data['mesh_mask'] = mesh_mask
         if 'uv_shaped_body' in self.signature.keys():
             uv_shaped_body = np.load(os.path.join(self.folder, 'uv_shaped_body', id + '.npz')); uv_shaped_body = uv_shaped_body['uv_shaped_body']; data['uv_shaped_body'] = uv_shaped_body
@@ -118,9 +135,13 @@ class StaticDataset():
 
 class DatasetIdx(tf.data.Dataset):
 
-    def __new__(cls, folder, shuffle=True):
+    def __new__(cls, folder, shuffle=True, is_cape=False):
         uv_static_folder = os.path.join(folder, 'pose_shape') 
         frames = sorted(os.listdir(uv_static_folder))
+
+        if is_cape:
+            frames = ['.'.join(frame.split('.')[:-1]) for frame in frames] # .split('_')[0]
+        else:
             frames = [frame.split('.')[0] for frame in frames] # .split('_')[0]
         if shuffle:
             random.shuffle(frames)
@@ -146,18 +167,22 @@ class DatasetFactory():
         return tf_signature
 
     
-    def get_dataset(self, folder, batch_size, signature, shuffle=True, use_filled=False, resolutions=[512], in_memory=False, do_repeat=True):
+    def get_dataset(self, folder, batch_size, signature, shuffle=True, use_filled=False, resolutions=[512], in_memory=False, do_repeat=True, is_cape=False):
         # assert (use_filled and len(resolutions) >= 1) or (not use_filled and len(resolutions) == 1)
         assert set(resolutions).issubset(set([32, 64, 128, 256, 512]))
 
         # static_data = StaticDataset(folder, signature)
-        dataset_idx = DatasetIdx(folder, shuffle)
+        dataset_idx = DatasetIdx(folder, shuffle, is_cape=is_cape)
         filled = ''
         if use_filled:
             filled = '_filled'
+        separator = '_'
+        if is_cape:
+            separator = '.'
+        
 
         def read_item(frame):
-            frame_split = tf.strings.split(frame, sep='_')
+            frame_split = tf.strings.split(frame, sep=separator)
             id, frame_nr = frame_split[0].numpy().decode("utf-8"), frame_split[1].numpy().decode("utf-8")
             # id, frame_nr = frame_split[0].numpy(), frame_split[1].numpy()
             # static_info = static_data[id]
@@ -166,7 +191,7 @@ class DatasetFactory():
             if 'id' in signature.keys():
                 item['id'] = id
             if 'pose_shape' in signature.keys():
-                pose_shape = np.load(os.path.join(folder, 'pose_shape',  id + '_' + frame_nr + '.npy'))
+                pose_shape = np.load(os.path.join(folder, 'pose_shape',  id + separator + frame_nr + '.npy'))
                 
                 ##############################
                 pose_shape[:3] = 0
@@ -174,7 +199,7 @@ class DatasetFactory():
 
                 item['pose_shape'] = pose_shape
             if 'uv_posed' in signature.keys():
-                uv_posed = np.load(os.path.join(folder, 'uv_posed', id + '_' + frame_nr + '.npz')); uv_posed = uv_posed['uv_gt']
+                uv_posed = np.load(os.path.join(folder, 'uv_posed', id + separator + frame_nr + '.npz')); uv_posed = uv_posed['uv_gt']
                 item['uv_posed'] = uv_posed
             # if 'uv_body_posed' in signature.keys():
             #     uv_body_posed = np.load(os.path.join(folder, 'uv_body_posed', id + '_' + frame_nr + '.npz')); uv_body_posed = uv_body_posed['uv_body']; uv_body_posed = np.transpose(uv_body_posed, [2, 0, 1])
@@ -187,10 +212,10 @@ class DatasetFactory():
             #     item['mesh_posed_body_no_orient'] = mesh_posed_body_no_orient
 
             if 'mesh_body_posed' in signature.keys():
-                mesh_posed_body_no_orient = np.load(os.path.join(folder, 'mesh_posed_body_no_orient', id + '_' + frame_nr + '.npz')); mesh_posed_body_no_orient = mesh_posed_body_no_orient['mesh_posed_body_no_orient']
+                mesh_posed_body_no_orient = np.load(os.path.join(folder, 'mesh_posed_body_no_orient', id + separator + frame_nr + '.npz')); mesh_posed_body_no_orient = mesh_posed_body_no_orient['mesh_posed_body_no_orient']
                 item['mesh_body_posed'] = mesh_posed_body_no_orient
             if 'mesh_posed' in signature.keys():
-                mesh_posed = np.load(os.path.join(folder, 'mesh_posed', id + '_' + frame_nr + '.npz')); mesh_posed = mesh_posed['mesh_posed']
+                mesh_posed = np.load(os.path.join(folder, 'mesh_posed', id + separator + frame_nr + '.npz')); mesh_posed = mesh_posed['mesh_posed']
                 item['mesh_posed'] = mesh_posed
             # if 'mesh_unposed' in signature.keys():
             #     mesh_unposed = np.load(os.path.join(folder, 'mesh_unposed', id + '_' + frame_nr + '.npz')); mesh_unposed = mesh_unposed['mesh_unposed']
@@ -199,12 +224,12 @@ class DatasetFactory():
             #     uv_unposed = np.load(os.path.join(folder, 'uv_unposed', id + '_' + frame_nr + '.npz')); uv_unposed = uv_unposed['uv_unposed']; uv_unposed = np.transpose(uv_unposed, [2, 0, 1])
             #     item['uv_unposed'] = uv_unposed
             if 'mesh_unposed' in signature.keys():
-                mesh_unposed_no_shape = np.load(os.path.join(folder, 'mesh_unposed_no_shape', id + '_' + frame_nr + '.npz')); mesh_unposed_no_shape = mesh_unposed_no_shape['mesh_unposed_no_shape']
+                mesh_unposed_no_shape = np.load(os.path.join(folder, 'mesh_unposed_no_shape', id + separator + frame_nr + '.npz')); mesh_unposed_no_shape = mesh_unposed_no_shape['mesh_unposed_no_shape']
                 item['mesh_unposed'] = mesh_unposed_no_shape
 
 
             if 'mesh_curvature' in signature.keys():
-                mesh_curvature = np.load(os.path.join(folder, 'mesh_curvature', id + '_' + frame_nr + '.npz')); mesh_curvature = mesh_curvature['mesh_curvature']
+                mesh_curvature = np.load(os.path.join(folder, 'mesh_curvature', id + separator + frame_nr + '.npz')); mesh_curvature = mesh_curvature['mesh_curvature']
                 item['mesh_curvature'] = mesh_curvature.astype(np.int32)
 
 
@@ -214,7 +239,7 @@ class DatasetFactory():
                     res_string = '_' + str(res)
 
                 if 'uv_curvature' + res_string in signature.keys():
-                    uv_curvature = np.load(os.path.join(folder, 'uv_curvature' + filled + res_string, id + '_' + frame_nr + '.npz')); 
+                    uv_curvature = np.load(os.path.join(folder, 'uv_curvature' + filled + res_string, id + separator + frame_nr + '.npz')); 
                     if filled != '' or res_string != '':
                         uv_curvature = uv_curvature['uv_curvature' + filled] 
                     else:
@@ -223,11 +248,11 @@ class DatasetFactory():
                     item['uv_curvature' + res_string] = uv_curvature
 
                 if 'uv_unposed' + res_string in signature.keys():
-                    uv_unposed_no_shape = np.load(os.path.join(folder, 'uv_unposed_no_shape' + filled + res_string, id + '_' + frame_nr + '.npz')); uv_unposed_no_shape = uv_unposed_no_shape['uv_unposed_no_shape' + filled]
+                    uv_unposed_no_shape = np.load(os.path.join(folder, 'uv_unposed_no_shape' + filled + res_string, id + separator + frame_nr + '.npz')); uv_unposed_no_shape = uv_unposed_no_shape['uv_unposed_no_shape' + filled]
                     item['uv_unposed' + res_string] = uv_unposed_no_shape
 
                 if 'uv_body_posed' + res_string in signature.keys():
-                    uv_posed_body_no_orient = np.load(os.path.join(folder, 'uv_posed_body_no_orient' + filled + res_string, id + '_' + frame_nr + '.npz')); uv_posed_body_no_orient = uv_posed_body_no_orient['uv_posed_body_no_orient' + filled]
+                    uv_posed_body_no_orient = np.load(os.path.join(folder, 'uv_posed_body_no_orient' + filled + res_string, id + separator + frame_nr + '.npz')); uv_posed_body_no_orient = uv_posed_body_no_orient['uv_posed_body_no_orient' + filled]
                     item['uv_body_posed' + res_string] = uv_posed_body_no_orient
 
 

downscale_cape.py

@@ -0,0 +1,208 @@
+import argparse
+import os
+import tqdm
+import cv2
+import tensorflow as tf
+import scipy.interpolate as spi
+import numpy as np
+import plotly.graph_objects as go
+import plotly.express as ex
+
+os.environ["CUDA_VISIBLE_DEVICES"] = "1"
+
+gpus = tf.config.experimental.list_physical_devices('GPU')
+if gpus:
+    try:
+        # Currently, memory growth needs to be the same across GPUs
+        for gpu in gpus:
+            tf.config.experimental.set_memory_growth(gpu, True)
+        logical_gpus = tf.config.experimental.list_logical_devices('GPU')
+        print(len(gpus), "Physical GPUs,", len(logical_gpus), "Logical GPUs")
+    except RuntimeError as e:
+        # Memory growth must be set before GPUs have been initialized
+        print(e)
+
+def get_img_idxs():
+    img_idxs = dict()
+    img_coords = dict()
+    uv_masks = dict()
+    uv_mask = np.load('custom_utils/mask_256x512.npy')
+    coords = np.transpose(np.stack(np.nonzero((1 - uv_mask))), (1,0))
+    img_idx = np.transpose(np.stack(np.nonzero((uv_mask))), (1,0))
+    img_idxs[512] = img_idx
+    img_coords[512] = coords
+    uv_masks[512] = uv_mask.astype(np.int32)
+    for res in [32, 64, 128, 256]:
+        down = tf.image.resize(uv_mask[:,:,tf.newaxis].astype(np.int32), size=(res, int(res/2)), method=tf.image.ResizeMethod.NEAREST_NEIGHBOR)
+        down = np.squeeze(down.numpy().astype(bool))
+        coords = np.transpose(np.stack(np.nonzero((1 - down))), (1,0))
+        img_idx = np.transpose(np.stack(np.nonzero((down))), (1,0))
+        img_idxs[res] = img_idx
+        img_coords[res] = coords
+        uv_masks[res] = down.astype(np.int32)
+
+    return img_idxs, img_coords, uv_masks
+
+
+def fill(img, mask):
+    coords = img_coords[img.shape[0]]
+    img_idx = img_idxs[img.shape[0]]
+    # coords = np.transpose(np.stack(np.nonzero((1 - uv_masks[img.shape[0]]))), (1,0))
+    # img_idx = np.transpose(np.stack(np.nonzero((uv_masks[img.shape[0]]))), (1,0))
+    img_data = img[img_idx[:,0], img_idx[:,1], :]
+
+    interpolator =  spi.NearestNDInterpolator(x=img_idx, y=img_data)
+    img_2 = interpolator(coords)
+    res = np.zeros((512,256,3), dtype=np.float32)
+    res[coords[:,0], coords[:,1], :] = img_2
+    res[img_idx[:,0], img_idx[:,1], :] = img_data
+
+    return res
+
+
+def fill_label(img, mask):
+    coords = img_coords[img.shape[0]]
+    img_idx = img_idxs[img.shape[0]]
+    img_data = img[img_idx[:,0], img_idx[:,1]]
+
+    interpolator =  spi.NearestNDInterpolator(x=img_idx, y=img_data)
+    img_2 = interpolator(coords)
+    res = np.zeros((512,256), dtype=np.float32)
+    res[coords[:,0], coords[:,1]] = img_2
+    res[img_idx[:,0], img_idx[:,1]] = img_data
+
+    return res
+
+
+def generate_downscaled_uv_map(folder, id, size):
+    img = np.load(os.path.join(folder, 'uv_mask', id + '.npz')); img = img['uv_mask'].astype(np.float32)
+    down = tf.image.resize(img[:,:,tf.newaxis], size=(size, int(size/2)), method=tf.image.ResizeMethod.NEAREST_NEIGHBOR)
+    down = np.squeeze(down.numpy().astype(bool))
+    np.savez_compressed(os.path.join(folder, 'uv_mask' + '_' + str(size), id + '.npz'), uv_mask = down)
+
+
+class UVMaskStore():
+    def __init__(self, folder, size):
+        self.size = size
+
+    def __getitem__(self, id) -> dict:
+        return uv_masks[self.size]
+
+
+def downscale_uv_maps_posed_body(folder, type, sizes):
+    for size in sizes:
+        os.makedirs(os.path.join(folder, type + '_' + str(size)), exist_ok=True)
+
+    frames = os.listdir(os.path.join(folder, type))[int(args.start):int(args.end)]
+
+    for frame in tqdm.tqdm(frames):
+        id, _ = frame.split('_')
+        img = np.load(os.path.join(folder, type, frame)); img = img['uv_posed_body_no_orient']
+        mask_full = uv_mask_store[512][id]
+        img = fill(img, mask_full)
+        for size in sizes:
+            mask = uv_mask_store[size][id]
+            down = tf.image.resize(img, size=(size, int(size/2)), method=tf.image.ResizeMethod.LANCZOS5)
+            down = down * mask[:,:,np.newaxis]
+            np.savez_compressed(os.path.join(folder, type + '_' + str(size), frame), uv_posed_body_no_orient = down)
+
+
+def downscale_uv_maps_curv(folder, type, sizes):
+    for size in sizes:
+        os.makedirs(os.path.join(folder, type + '_' + str(size)), exist_ok=True)
+
+    frames = os.listdir(os.path.join(folder, type))[int(args.start):int(args.end)]
+
+    for frame in tqdm.tqdm(frames):
+        id, _ = frame.split('_')
+        img = np.load(os.path.join(folder, type, frame)); img = img['curvature_uv']
+        mask_full = uv_mask_store[512][id]
+        img = fill_label(img, mask_full)
+        for size in sizes:
+            mask = uv_mask_store[size][id]
+            down = tf.image.resize(img[:,:,tf.newaxis], size=(size, int(size/2)), method=tf.image.ResizeMethod.NEAREST_NEIGHBOR)
+            down = np.squeeze(down) * mask[:,:]
+            np.savez_compressed(os.path.join(folder, type + '_' + str(size), frame), uv_curvature = down)
+
+
+
+def downscale_uv_maps_unposed(folder, type, sizes):
+    for size in sizes:
+        os.makedirs(os.path.join(folder, type + '_' + str(size)), exist_ok=True)
+
+    frames = os.listdir(os.path.join(folder, type))[int(args.start):int(args.end)]
+
+    for frame in tqdm.tqdm(frames):
+        id, _ = frame.split('_')
+        img = np.load(os.path.join(folder, type, frame)); img = img['uv_unposed_no_shape']
+        mask_full = uv_mask_store[512][id]
+        img = fill(img, mask_full)
+        for size in sizes:
+            mask = uv_mask_store[size][id]
+            down = tf.image.resize(img, size=(size, int(size/2)), method=tf.image.ResizeMethod.LANCZOS5)
+            down = down * mask[:,:,np.newaxis]
+            np.savez_compressed(os.path.join(folder, type + '_' + str(size), frame), uv_unposed_no_shape = down)
+
+
+def downscale_uv_maps_static(folder, type, sizes):
+    for size in sizes:
+        os.makedirs(os.path.join(folder, type + '_' + str(size)), exist_ok=True)
+
+    frames = os.listdir(os.path.join(folder, type))[int(args.start):int(args.end)]
+
+    for frame in tqdm.tqdm(frames):
+        id, _ = frame.split('.')
+        img = np.load(os.path.join(folder, type, frame)); img = img['uv_static']
+        mask_full = uv_mask_store[512][id]
+        img = fill(img, mask_full)
+
+        for size in sizes:
+            down = tf.image.resize(img, size=(size, int(size/2)), method=tf.image.ResizeMethod.LANCZOS5)
+            mask = uv_mask_store[size][id]
+            down = down * mask[:,:,np.newaxis]
+            np.savez_compressed(os.path.join(folder, type + '_' + str(size), frame), uv_static = down)
+
+
+def downscale_uv_maps_mask(folder, type, size):
+    os.makedirs(os.path.join(folder, type + '_' + str(size)), exist_ok=True)
+
+    frames = os.listdir(os.path.join(folder, type))[int(args.start):int(args.end)]
+
+    for frame in tqdm.tqdm(frames):
+        id, _ = frame.split('.')
+        img = np.load(os.path.join(folder, type, frame)); img = img['uv_mask'].astype(np.float32)
+        down = tf.image.resize(img[:,:,tf.newaxis], size=(size, int(size/2)), method=tf.image.ResizeMethod.NEAREST_NEIGHBOR)
+        down = np.squeeze(down.numpy().astype(bool))
+        np.savez_compressed(os.path.join(folder, type + '_' + str(size), frame), uv_mask = down)
+
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument("-f", "--folder", help = "end of range", default='/home/workspace/local-data/cape_processed/test/male')
+    parser.add_argument("-s", "--start", help = "start of range", default=0)
+    parser.add_argument("-e", "--end", help = "end of range", default=10000)
+    parser.add_argument("-n", "--name", help = "end of range", default='lhunor')
+    args = parser.parse_args()
+
+
+    sizes = [32, 64, 128, 256]
+    folder = args.folder
+
+    img_idxs, img_coords, uv_masks = get_img_idxs()
+
+    uv_mask_store = { size: UVMaskStore(folder, size=size) for size in sizes }
+    uv_mask_store[512] = UVMaskStore(folder, size=512)
+
+    # downscale_uv_maps_mask(folder=folder, type='uv_mask', size=32)
+    # downscale_uv_maps_mask(folder=folder, type='uv_mask', size=64)
+    # downscale_uv_maps_mask(folder=folder, type='uv_mask', size=128)
+    # downscale_uv_maps_mask(folder=folder, type='uv_mask', size=256)
+    downscale_uv_maps_static(folder=folder, type='uv_static', sizes=sizes)
+
+    # downscale_uv_maps_unposed(folder=folder, type='uv_unposed_no_shape', sizes=sizes)
+    # downscale_uv_maps_curv(folder=folder, type='uv_curvature', sizes=sizes)
+    # downscale_uv_maps_posed_body(folder=folder, type='uv_posed_body_no_orient', sizes=sizes)
+
+
+    print()