File size: 7,210 Bytes
8870024 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 |
#!/usr/bin/env python2
# -*- coding: utf-8 -*-
import cv2
import h5py
import argparse
import numpy as np
import cPickle as pkl
from opendr.renderer import ColoredRenderer
from opendr.camera import ProjectPoints
from opendr.geometry import VertNormals
from tex.iso import Isomapper, IsoColoredRenderer
from util import im
from util.logger import log
from models.smpl import Smpl
def main(consensus_file, camera_file, video_file, pose_file, masks_file, out, model_file, resolution, num,
first_frame, last_frame, display):
# load data
with open(model_file, 'rb') as fp:
model_data = pkl.load(fp)
with open(camera_file, 'rb') as fp:
camera_data = pkl.load(fp)
with open(consensus_file, 'rb') as fp:
consensus_data = pkl.load(fp)
pose_data = h5py.File(pose_file, 'r')
poses = pose_data['pose'][first_frame:last_frame]
trans = pose_data['trans'][first_frame:last_frame]
masks = h5py.File(masks_file, 'r')['masks'][first_frame:last_frame]
num_frames = masks.shape[0]
indices_texture = np.ceil(np.arange(num) * num_frames * 1. / num).astype(np.int)
vt = np.load('assets/basicModel_vt.npy')
ft = np.load('assets/basicModel_ft.npy')
# init
base_smpl = Smpl(model_data)
base_smpl.betas[:] = consensus_data['betas']
base_smpl.v_personal[:] = consensus_data['v_personal']
bgcolor = np.array([1., 0.2, 1.])
iso = Isomapper(vt, ft, base_smpl.f, resolution, bgcolor=bgcolor)
iso_vis = IsoColoredRenderer(vt, ft, base_smpl.f, resolution)
camera = ProjectPoints(t=camera_data['camera_t'], rt=camera_data['camera_rt'], c=camera_data['camera_c'],
f=camera_data['camera_f'], k=camera_data['camera_k'], v=base_smpl)
frustum = {'near': 0.1, 'far': 1000., 'width': int(camera_data['width']), 'height': int(camera_data['height'])}
rn_vis = ColoredRenderer(f=base_smpl.f, frustum=frustum, camera=camera, num_channels=1)
cap = cv2.VideoCapture(video_file)
for _ in range(first_frame):
cap.grab()
# get part-textures
i = first_frame
tex_agg = np.zeros((resolution, resolution, 25, 3))
tex_agg[:] = np.nan
normal_agg = np.ones((resolution, resolution, 25)) * 0.2
vn = VertNormals(f=base_smpl.f, v=base_smpl)
static_indices = np.indices((resolution, resolution))
while cap.isOpened() and i < indices_texture[-1]:
if i in indices_texture:
log.info('Getting part texture from frame {}...'.format(i))
_, frame = cap.read()
mask = np.array(masks[i], dtype=np.uint8)
pose_i = np.array(poses[i], dtype=np.float32)
trans_i = np.array(trans[i], dtype=np.float32)
base_smpl.pose[:] = pose_i
base_smpl.trans[:] = trans_i
# which faces have been seen and are projected into the silhouette?
visibility = rn_vis.visibility_image.ravel()
visible = np.nonzero(visibility != 4294967295)[0]
proj = camera.r
in_viewport = np.logical_and(
np.logical_and(np.round(camera.r[:, 0]) >= 0, np.round(camera.r[:, 0]) < frustum['width']),
np.logical_and(np.round(camera.r[:, 1]) >= 0, np.round(camera.r[:, 1]) < frustum['height']),
)
in_mask = np.zeros(camera.shape[0], dtype=np.bool)
idx = np.round(proj[in_viewport][:, [1, 0]].T).astype(np.int).tolist()
in_mask[in_viewport] = mask[idx]
faces_in_mask = np.where(np.min(in_mask[base_smpl.f], axis=1))[0]
visible_faces = np.intersect1d(faces_in_mask, visibility[visible])
# get the current unwrap
part_tex = iso.render(frame / 255., camera, visible_faces)
# angle under which the texels have been seen
points = np.hstack((proj, np.ones((proj.shape[0], 1))))
points3d = camera.unproject_points(points)
points3d /= np.linalg.norm(points3d, axis=1).reshape(-1, 1)
alpha = np.sum(points3d * -vn.r, axis=1).reshape(-1, 1)
alpha[alpha < 0] = 0
iso_normals = iso_vis.render(alpha)[:, :, 0]
iso_normals[np.all(part_tex == bgcolor, axis=2)] = 0
# texels to consider
part_mask = np.zeros((resolution, resolution))
min_normal = np.min(normal_agg, axis=2)
part_mask[iso_normals > min_normal] = 1.
# update best seen texels
where = np.argmax(np.atleast_3d(iso_normals) - normal_agg, axis=2)
idx = np.dstack((static_indices[0], static_indices[1], where))[part_mask == 1]
tex_agg[list(idx[:, 0]), list(idx[:, 1]), list(idx[:, 2])] = part_tex[part_mask == 1]
normal_agg[list(idx[:, 0]), list(idx[:, 1]), list(idx[:, 2])] = iso_normals[part_mask == 1]
if display:
im.show(part_tex, id='part_tex', waittime=1)
else:
cap.grab()
i += 1
# merge textures
log.info('Computing median texture...')
tex_median = np.nanmedian(tex_agg, axis=2)
log.info('Inpainting unseen areas...')
where = np.max(normal_agg, axis=2) > 0.2
tex_mask = iso.iso_mask
mask_final = np.float32(where)
kernel_size = np.int(resolution * 0.02)
kernel = np.ones((kernel_size, kernel_size), np.uint8)
inpaint_area = cv2.dilate(tex_mask, kernel) - mask_final
tex_final = cv2.inpaint(np.uint8(tex_median * 255), np.uint8(inpaint_area * 255), 3, cv2.INPAINT_TELEA)
cv2.imwrite(out, tex_final)
log.info('Done.')
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument(
'consensus',
type=str,
help="pkl file that contains consensus")
parser.add_argument(
'camera',
type=str,
help="pkl file that contains camera settings")
parser.add_argument(
'video',
type=str,
help="Input video")
parser.add_argument(
'pose_file',
type=str,
help="File that contains poses")
parser.add_argument(
'masks_file',
type=str,
help="File that contains segmentations")
parser.add_argument(
'out',
type=str,
help="Out file path")
parser.add_argument(
'--model', '-m',
default='vendor/smpl/models/basicmodel_m_lbs_10_207_0_v1.0.0.pkl',
help='Path to SMPL model')
parser.add_argument(
'--resolution', '-r', default=1000, type=int,
help="Output resolution")
parser.add_argument(
'--num', '-n', default=120, type=int,
help="Number of used frames")
parser.add_argument(
'--first_frame', '-f', default=0, type=int,
help="First frame to use")
parser.add_argument(
'--last_frame', '-l', default=2000, type=int,
help="Last frame to use")
parser.add_argument(
'--display', '-d',
action='store_true',
help="Enable visualization")
args = parser.parse_args()
main(args.consensus, args.camera, args.video, args.pose_file, args.masks_file, args.out, args.model,
args.resolution, args.num, args.first_frame, args.last_frame, args.display)
|