You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
abbb5d136d | 4 years ago | |
---|---|---|
.idea | 4 years ago | |
configs | 4 years ago | |
.gitignore | 4 years ago | |
README.md | 4 years ago | |
data_loader_split.py | 4 years ago | |
data_verifier.py | 4 years ago | |
ddp_model.py | 4 years ago | |
ddp_test_nerf.py | 4 years ago | |
ddp_train_nerf.py | 4 years ago | |
environment.yml | 4 years ago | |
nerf_network.py | 4 years ago | |
nerf_sample_ray_split.py | 4 years ago | |
utils.py | 4 years ago |
README.md
NeRF++
Codebase for paper:
- Work with 360 capture of large-scale unbounded scenes.
- Support multi-gpu training and inference.
Data
- Download our preprocessed data from tanks_and_temples, lf_data.
- Put the data in the code directory.
- Data format. ** Each scene consists of 3 splits: train/test/validation. ** Intrinsics and poses are stored as flattened 4x4 matrices. ** Opencv camera coordinate system is adopted, i.e., x--->right, y--->down, z--->scene.
- Scene normalization: move the average camera center to origin, and put all the camera centers inside the unit sphere.
Training
python ddp_train_nerf.py --config configs/tanks_and_temples/tat_training_truck.txt
Testing
python ddp_test_nerf.py --config configs/tanks_and_temples/tat_training_truck.txt --render_splits test,camera_path