BiohazardVFX/4DGaussians
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #103 from jsxzs/master

Browse Source 
add preprocess_dynerf.py and update README
This commit is contained in:
Geralt_of_Rivia 2024-03-20 09:58:19 +01:00 committed by GitHub
commit 0b0b1a2d78
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
4 changed files with 30 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
README.md
View File

@ -93,6 +93,18 @@ For training synthetic scenes such as `bouncingballs`, run
python train.py -s data/dnerf/bouncingballs --port 6017 --expname "dnerf/bouncingballs" --configs arguments/dnerf/bouncingballs.py python train.py -s data/dnerf/bouncingballs --port 6017 --expname "dnerf/bouncingballs" --configs arguments/dnerf/bouncingballs.py
``` ```
For training dynerf scenes such as `cut_roasted_beef`, run
```python
# First, extract the frames of each video.
python scripts/preprocess_dynerf.py --datadir data/dynerf/cut_roasted_beef
# Second, generate point clouds from input data.
bash colmap.sh data/dynerf/cut_roasted_beef llff
# Third, downsample the point clouds generated in the second step.
python scripts/downsample_point.py data/dynerf/cut_roasted_beef/colmap/dense/workspace/fused.ply data/dynerf/cut_roasted_beef/points3D_downsample2.ply
# Finally, train.
python train.py -s data/dynerf/cut_roasted_beef --port 6017 --expname "dynerf/cut_roasted_beef" --configs arguments/dynerf/cut_roasted_beef.py
```
You can customize your training config through the config files. You can customize your training config through the config files.
Checkpoint Checkpoint

2
scene/neural_3D_dataset_NDC.py
View File

@ -262,7 +262,7 @@ class Neural3D_NDC_Dataset(Dataset):
poses_arr = np.load(os.path.join(self.root_dir, "poses_bounds.npy")) poses_arr = np.load(os.path.join(self.root_dir, "poses_bounds.npy"))
poses = poses_arr[:, :-2].reshape([-1, 3, 5]) # (N_cams, 3, 5) poses = poses_arr[:, :-2].reshape([-1, 3, 5]) # (N_cams, 3, 5)
self.near_fars = poses_arr[:, -2:] self.near_fars = poses_arr[:, -2:]
videos = glob.glob(os.path.join(self.root_dir, "cam*")) videos = glob.glob(os.path.join(self.root_dir, "cam*.mp4"))
videos = sorted(videos) videos = sorted(videos)
# breakpoint() # breakpoint()
assert len(videos) == poses_arr.shape[0] assert len(videos) == poses_arr.shape[0]

4
scripts/llff2colmap.py
View File

@ -91,7 +91,7 @@ if not os.path.exists(colmap_dir):
poses_arr = np.load(os.path.join(root_dir, "poses_bounds.npy")) poses_arr = np.load(os.path.join(root_dir, "poses_bounds.npy"))
poses = poses_arr[:, :-2].reshape([-1, 3, 5]) # (N_cams, 3, 5) poses = poses_arr[:, :-2].reshape([-1, 3, 5]) # (N_cams, 3, 5)
near_fars = poses_arr[:, -2:] near_fars = poses_arr[:, -2:]
videos = glob.glob(os.path.join(root_dir, "cam*")) videos = glob.glob(os.path.join(root_dir, "cam[0-9][0-9]"))
videos = sorted(videos) videos = sorted(videos)
assert len(videos) == poses_arr.shape[0] assert len(videos) == poses_arr.shape[0]
H, W, focal = poses[0, :, -1] H, W, focal = poses[0, :, -1]
@ -109,7 +109,7 @@ poses = np.concatenate([poses[..., 1:2], -poses[..., :1], poses[..., 2:4]], -1)
# poses[..., 3] /= scale_factor # poses[..., 3] /= scale_factor
# Sample N_views poses for validation - NeRF-like camera trajectory. # Sample N_views poses for validation - NeRF-like camera trajectory.
# val_poses = directions # val_poses = directions
videos = glob.glob(os.path.join(root_dir, "cam*")) videos = glob.glob(os.path.join(root_dir, "cam[0-9][0-9]"))
videos = sorted(videos) videos = sorted(videos)
image_paths = [] image_paths = []
for index, video_path in enumerate(videos): for index, video_path in enumerate(videos):

15
scripts/preprocess_dynerf.py Normal file
View File

@ -0,0 +1,15 @@
from argparse import ArgumentParser
import sys
sys.path.append('./scene')
from neural_3D_dataset_NDC import Neural3D_NDC_Dataset
# import scene
# from scene.neural_3D_dataset_NDC import Neural3D_NDC_Dataset
if __name__ == '__main__':
parser = ArgumentParser(description="Extract images from dynerf videos")
parser.add_argument("--datadir", default='data/dynerf/cut_roasted_beef', type=str)
args = parser.parse_args()
train_dataset = Neural3D_NDC_Dataset(args.datadir, "train", 1.0, time_scale=1,
scene_bbox_min=[-2.5, -2.0, -1.0], scene_bbox_max=[2.5, 2.0, 1.0], eval_index=0)
test_dataset = Neural3D_NDC_Dataset(args.datadir, "test", 1.0, time_scale=1,
scene_bbox_min=[-2.5, -2.0, -1.0], scene_bbox_max=[2.5, 2.0, 1.0], eval_index=0)