248 lines
12 KiB
Python
248 lines
12 KiB
Python
import os
|
|
import sys
|
|
|
|
os.environ["CUDA_VISIBLE_DEVICES"] = '0'
|
|
|
|
import math
|
|
import time
|
|
import torch
|
|
import kornia
|
|
import pytorch3d
|
|
import torchvision as tv
|
|
import numpy as np
|
|
import scipy.io as sio
|
|
import plotly.express as ex
|
|
|
|
from torch.utils.data import Dataset
|
|
|
|
|
|
sys.path.append(os.path.dirname(os.path.abspath(__file__)) + '/..')
|
|
from data.render import Render, DepthRenderer
|
|
from superSMPL.IO import readPC2Frame, writePC2
|
|
from utils.data_utils import Frame, read_frames_file, mask_faces, get_normals_from_depth
|
|
from cloth3d.read import DataReader
|
|
from cloth3d.util import quads2tris
|
|
|
|
|
|
class Dataset(Dataset):
|
|
def __init__(self, folder, folder_rgb, frames_file='frames_all.txt', device='cuda', use_cache=True, random_view=True):
|
|
self.folder = folder
|
|
self.folder_rgb = folder_rgb
|
|
self.device = device
|
|
self.random_view = random_view
|
|
|
|
self.transforms = tv.transforms.ToTensor()
|
|
self.frames = read_frames_file(os.path.join(folder, frames_file))
|
|
self.render = DepthRenderer()
|
|
self.deodr_render : Render = Render(max_depth=10)
|
|
self.body_faces = np.load('custom_data/smpl_faces.npy')
|
|
self.reader = DataReader(folder, 'superSMPL')
|
|
|
|
|
|
self.cache = dict() if use_cache else None
|
|
|
|
def __len__(self):
|
|
return len(self.frames)
|
|
|
|
|
|
# TODO: make it work with two part outfits
|
|
def __getitem__(self, idx):
|
|
frame : Frame = self.frames[idx]
|
|
if self.cache is not None:
|
|
if frame in self.cache.keys():
|
|
return self.cache[frame]
|
|
|
|
path = os.path.join(self.folder, frame.id)
|
|
info = self.reader.read_info(frame.id)
|
|
zrot = info['zrot'] # if not self.random_view else (((np.random.random(1) * 2) -1) * np.pi)[0]
|
|
trans = info['trans'][:,frame.frame_nr]
|
|
# mesh_posed = readPC2Frame(os.path.join(path, frame.garment + '_registered.pc16'), frame.frame_nr, True)
|
|
|
|
mesh_posed = self.reader.read_garment_vertices(frame.id, frame.garment, frame.frame_nr, trans, zrot)
|
|
mesh_posed = torch.tensor(mesh_posed, device=self.device)
|
|
# mesh_posed_no_trans = self.reader.read_garment_vertices(frame.id, frame.garment, frame.frame_nr, absolute=False)
|
|
|
|
mesh_mask = np.load(os.path.join(path, frame.garment + '_mask.npy'))
|
|
# TODO: what's the difference between masking and reading .obj file. is the obj file the not registered version?
|
|
faces = mask_faces(self.body_faces, mesh_mask)
|
|
# faces = quads2tris(self.reader.read_garment_topology(frame.id, frame.garment))
|
|
# body = readPC2Frame(os.path.join(path, 'Body_posed.pc16'), frame.frame_nr, True)
|
|
body, body_faces, root_joint, joints, joints_no_trans = self.reader.read_human(frame.id, frame.frame_nr, trans, zrot)
|
|
# body_no_trans, _, _, _, _ = self.reader.read_human(frame.id, frame.frame_nr, absolute=False)
|
|
body_faces = quads2tris(body_faces)
|
|
|
|
if self.random_view:
|
|
x_angle = (torch.rand(1, device=self.device) * 2 * torch.pi - torch.pi) / 10
|
|
y_angle = (torch.rand(1, device=self.device) * 2 * torch.pi - torch.pi) / 10
|
|
z_angle = (torch.rand(1, device=self.device) * 2 * torch.pi - torch.pi)
|
|
view = pytorch3d.transforms.axis_angle_to_matrix(torch.concat((x_angle, y_angle, z_angle)))
|
|
|
|
transform = pytorch3d.transforms.Rotate(view)
|
|
mesh_posed = transform.transform_points(mesh_posed)
|
|
body = transform.transform_points(body)
|
|
else:
|
|
view = torch.eye(3)
|
|
|
|
combined = torch.Tensor(np.concatenate((body, mesh_posed[mesh_mask, :]))).to(self.device)
|
|
# combined_no_trans = torch.Tensor(np.concatenate((body_no_trans, mesh_posed_no_trans[mesh_mask, :]))).to('cuda')
|
|
combined_faces = torch.Tensor(np.concatenate((body_faces, faces + body.shape[0]))).to(self.device)
|
|
|
|
|
|
|
|
start = time.perf_counter()
|
|
# depth_image = self.render.render(mesh_posed[mask, :], faces, info['camLoc'][0])[:,:,0]
|
|
# depth_image = self.render.render(combined, combined_faces, info['camLoc'][0])[:,:,0]
|
|
deodr_depth = self.deodr_render.render(cam=info['camLoc'].astype(np.float32), mesh=combined.cpu().numpy(), faces=combined_faces.cpu().numpy().astype(np.int32))
|
|
# deodr_depth = self.deodr_render.render(cam=info['camLoc'].astype(np.float32), mesh=combined, faces=combined_faces.cpu().numpy().astype(np.int32))
|
|
print(f'deodr time: {time.perf_counter() - start}')
|
|
|
|
start = time.perf_counter()
|
|
depth_image, depth_mask, v2i, K, camera, pix_to_face = self.render(combined, combined_faces, info['camLoc'])
|
|
# cam_no_trans = info['camLoc'].copy()
|
|
# cam_no_trans[1:] = 0
|
|
# depth_image_no_trans, depth_mask_no_trans, _, _, camera_no_trans, _ = self.render(combined_no_trans, combined_faces, cam_no_trans)
|
|
print(f'pytorch3d time: {time.perf_counter() - start}')
|
|
|
|
start = time.perf_counter()
|
|
# TODO: is it sure I need this K, and not some transformed one?
|
|
normal_image = get_normals_from_depth(depth_image[None,None,:,:], depth_mask[None,:,:], K)
|
|
print(f'normals time: {time.perf_counter() - start}')
|
|
|
|
depth_mask_body = (pix_to_face <= body_faces.shape[0]) * depth_mask
|
|
depth_mask_garment = (pix_to_face > body_faces.shape[0]) * depth_mask
|
|
|
|
|
|
# root_joint_pixel = camera.transform_points_screen(torch.tensor(root_joint.astype(np.float32), device=combined.get_device()))[0,:2].round()
|
|
# joints_pixel = camera.transform_points_screen(torch.tensor(joints.astype(np.float32), device=combined.get_device()))[0,:,:2]
|
|
# joints_no_trans_pixel = camera_no_trans.transform_points_screen(torch.tensor(joints_no_trans.astype(np.float32), device=combined.get_device()))[0,:,:2]
|
|
# ratio = ((joints_pixel[1,:] - joints_pixel[2,:]) ** 2).sum().sqrt() / ((joints_no_trans_pixel[1,:] - joints_no_trans_pixel[2,:]) ** 2).sum().sqrt()
|
|
|
|
# center_offset = torch.tensor([240, 320], device=root_joint_pixel.get_device()) - root_joint_pixel
|
|
# center_offset_ratio = center_offset / torch.tensor([480, 640], device=root_joint_pixel.get_device())
|
|
# bbox = tv.ops.masks_to_boxes(depth_mask[None,:,:])[0,:]
|
|
# width = bbox[2] - bbox[0]
|
|
# height = bbox[3] - bbox[1]
|
|
# width = width + (width % 2)
|
|
# height = height + (height % 2)
|
|
# dims = torch.tensor([width, height], device=width.get_device())
|
|
# # crop_size = torch.max(dims)
|
|
# # top = (root_joint_pixel[1] - height / 2).round().to(torch.int64)
|
|
# # left = (root_joint_pixel[0] - width / 2).round().to(torch.int64)
|
|
|
|
# cropped = tv.transforms.functional.crop(depth_image, bbox[1].to(torch.int64), bbox[0].to(torch.int64), height.to(torch.int64), width.to(torch.int64))
|
|
# new_root_joint_pixel = root_joint_pixel - bbox[:2]
|
|
# offset = dims / 2 - new_root_joint_pixel
|
|
# bbox[:2] = bbox[:2] - offset
|
|
# dims = dims + torch.abs(offset)
|
|
|
|
# cropped_2 = tv.transforms.functional.crop(depth_image, bbox[1].to(torch.int64), bbox[0].to(torch.int64), dims[1].to(torch.int64), dims[0].to(torch.int64))
|
|
|
|
|
|
# left = torch.tensor([0], device=bbox.get_device())
|
|
# right = torch.tensor([0], device=bbox.get_device())
|
|
# top = torch.tensor([0], device=bbox.get_device())
|
|
# bottom = torch.tensor([0], device=bbox.get_device())
|
|
# if offset[0] > 0:
|
|
# left = 2 * offset[0]
|
|
# else:
|
|
# right = -1 * 2 * offset[0]
|
|
# if offset[1] > 0:
|
|
# top = 2 * offset[1]
|
|
# else:
|
|
# bottom = -1 * 2 * offset[1]
|
|
# # centered = tv.transforms.functional.crop(cropped, new_top.to(torch.int64), new_left.to(torch.int64), new_height.to(torch.int64), new_width.to(torch.int64))
|
|
# centered = torch.nn.functional.pad(cropped, (left.to(torch.int64), right.to(torch.int64), top.to(torch.int64), bottom.to(torch.int64)), value=-1)
|
|
# orig = depth_image[root_joint_pixel.to(torch.int64)[1], root_joint_pixel.to(torch.int64)[0]].cpu().numpy()
|
|
# new = centered[(centered.shape[0] // 2), (centered.shape[1] // 2)].cpu().numpy()
|
|
# assert new == orig, 'Center pad did not work'
|
|
|
|
# scaled = tv.transforms.Resize((centered.shape[1] / ratio).round().int().item(), interpolation=tv.transforms.functional.InterpolationMode.NEAREST)(centered[None,None,:,:])[0,0,:,:]
|
|
# left, right = math.floor((depth_image.shape[1] - scaled.shape[1]) / 2), round((depth_image.shape[1] - scaled.shape[1]) / 2)
|
|
# top, bottom = math.floor((depth_image.shape[0] - scaled.shape[0]) / 2), round((depth_image.shape[0] - scaled.shape[0]) / 2)
|
|
# upscaled = torch.nn.functional.pad(scaled, (left, right, top, bottom), value=-1)
|
|
|
|
|
|
# Testing
|
|
# pc = kornia.geometry.depth.depth_to_3d(depth_image[None,None,:,:], K, normalize_points=True)
|
|
# pc = pc[0,:,depth_mask].cpu().numpy()
|
|
|
|
all_faces = combined_faces
|
|
visible_faces_idx = pix_to_face * depth_mask
|
|
visible_faces_idx = visible_faces_idx[torch.nonzero(visible_faces_idx, as_tuple=True)]
|
|
visible_vertices = torch.unique(torch.flatten(all_faces[visible_faces_idx, :])).to(torch.long)
|
|
visible_vertices_mask = (v2i[visible_vertices, 1] < depth_image.shape[0]) * (v2i[visible_vertices, 0] < depth_image.shape[1])
|
|
visible_vertices = visible_vertices[visible_vertices_mask]
|
|
visible_pixels_mask = depth_image[v2i[visible_vertices, 1], v2i[visible_vertices, 0]] != -1
|
|
visible_vertices = visible_vertices[visible_pixels_mask]
|
|
|
|
x = combined[visible_vertices, :]
|
|
y = np.array(info['camLoc'], dtype=np.float32)
|
|
dist = torch.sqrt(torch.sum((x - torch.tensor(y[None,:], device=x.get_device())) ** 2, axis=-1))
|
|
dist_img = depth_image[v2i[visible_vertices, 1], v2i[visible_vertices, 0]]
|
|
diff = torch.mean(torch.abs(dist - dist_img))
|
|
|
|
# combined = combined.cpu().numpy()
|
|
# depth_image = depth_image.cpu().numpy()
|
|
# dist_img = depth_image[v2i[idx, 1], v2i[idx, 0]]
|
|
|
|
# depth_image[v2i[visible_vertices, 1], v2i[visible_vertices, 0]] = 10
|
|
|
|
# diff = np.abs(dist - dist_img)
|
|
|
|
# import plotly.express as ex
|
|
# import plotly.graph_objects as go
|
|
# ex.imshow(deodr_depth[:,:,0]).show()
|
|
# ex.imshow(depth_image.cpu().numpy()).show()
|
|
# ex.imshow(normal_image[0].cpu().numpy()).show()
|
|
|
|
# trans = np.array(info['trans'], dtype=np.float32)[:, self.frames[idx].frame_nr]
|
|
# root = info['camLoc'].copy()
|
|
# root[1:] = 0
|
|
# go.Figure(data = [go.Scatter3d(x=combined[:, 0], y=combined[:, 1], z=combined[:, 2], marker=dict(size=3, line=dict(width=0)), mode='markers'),
|
|
# go.Scatter3d(x=[combined[idx, 0]], y=[combined[idx, 1]], z=[combined[idx, 2]], marker=dict(size=10, line=dict(width=0)), mode='markers'),
|
|
# go.Scatter3d(x=[root[0]], y=[root[1]], z=[root[2]], marker=dict(size=10, line=dict(width=0)), mode='markers'),
|
|
# ]).show()
|
|
|
|
# go.Figure(data = [go.Scatter3d(x=pc[0,:], y=pc[1,:], z=pc[2,:], marker=dict(size=3, line=dict(width=0)), mode='markers'),
|
|
# ]).show()
|
|
|
|
# v2i_coverage = np.zeros((480, 640), dtype=np.float32)
|
|
# v2i_coverage[v2i[:,0], v2i[:, 1]] = 1
|
|
# ex.imshow(v2i_coverage).show()
|
|
|
|
rgb_image = tv.io.read_image(os.path.join(self.folder_rgb, frame.id, f'{frame.frame_nr:04d}.png'), mode=tv.io.ImageReadMode.RGB).to(torch.float32)
|
|
|
|
# view = torch.tensor(np.concatenate((np.array([zrot], dtype=np.float32), info['camLoc'].astype(np.float32), trans.astype(np.float32)), axis=0), device=self.device)
|
|
|
|
|
|
# image = self.transforms(image)
|
|
data = { 'mesh_posed': mesh_posed,
|
|
'depth_image': depth_image,
|
|
'mesh_mask': mesh_mask,
|
|
'depth_mask': depth_mask,
|
|
'normal_image': normal_image,
|
|
'depth_mask_garment': depth_mask_garment,
|
|
'depth_mask_body': depth_mask_body,
|
|
'rgb_image': rgb_image.to(self.device),
|
|
'view': view,
|
|
}
|
|
|
|
self.cache[frame] = data
|
|
return self.cache[frame]
|
|
|
|
|
|
if __name__ == '__main__':
|
|
from torch.utils.data import DataLoader
|
|
|
|
device = "cuda" if torch.cuda.is_available() else "cpu"
|
|
|
|
# dataset = Dataset('/home/workspace/local-data/train')
|
|
dataset = Dataset('dataset/CLOTH3D/train', 'dataset/CLOTH3D2RGB/train', 'frames_all.txt')
|
|
train_dataloader = DataLoader(dataset, batch_size=4, drop_last=True, shuffle=False)
|
|
|
|
for batch in train_dataloader:
|
|
batch
|
|
pass
|
|
|
|
pass
|