https://yushiangw.github.io/factorednerf/
The repository of FactoredNeRF (SGP2023)
https://yushiangw.github.io/factorednerf/
Last synced: 25 days ago
JSON representation
The repository of FactoredNeRF (SGP2023)
- Host: GitHub
- URL: https://yushiangw.github.io/factorednerf/
- Owner: yushiangw
- License: apache-2.0
- Created: 2023-04-21T06:05:09.000Z (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2023-07-01T08:03:51.000Z (almost 2 years ago)
- Last Synced: 2024-10-30T07:47:48.661Z (6 months ago)
- Language: Python
- Homepage: https://geometry.cs.ucl.ac.uk/projects/2023/factorednerf/
- Size: 4.73 MB
- Stars: 6
- Watchers: 5
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-scene-representation - Factored Neural Representation for Scene Understanding
README
# Factored Neural Representation for Scene Understanding
[[Project Website]](https://geometry.cs.ucl.ac.uk/projects/2023/factorednerf/)
[[Arxiv]](https://arxiv.org/abs/2304.10950)
[[Dataset (6GB)]](https://geometry.cs.ucl.ac.uk/projects/2023/factorednerf/paper_docs/dataset)
---
## Installation:
1. cd to the unzip directory
2. build our docker image
````docker build -t factnerf -f Dockerfile . ````
3. download our dataset and put it at $FACTNERF_ROOT/data
````
$FACTNERF_ROOT/data/SYN
$FACTNERF_ROOT/data/SYN/sce_a_train
...
````
## Run in a Docker container:
````
export FACTNERF_ROOT=$(pwd)
# check if input data exists
ls $FACTNERF_ROOT/data
# set GPU
export CUDA_VISIBLE_DEVICES=0
````
Training
````
cd $FACTNERF_ROOT
python framework/run_main.py -f configs/SYN/factorednerf/sce_a.yaml --mode train
````
Rendering
````
#faster rendering using a smaller resolution
python framework/run_main.py -f configs/SYN/factorednerf/sce_a.yaml --mode render_valid_q -c map__final --dw 4 --fnum 4
# rendering (no downsampling)
python framework/run_main.py -f configs/SYN/factorednerf/sce_a.yaml --mode render_valid_q -c map__final --dw 1
````
## Checkpoints
Please download the checkpoint file [output-syn.zip](https://geometry.cs.ucl.ac.uk/projects/2023/factorednerf/paper_docs/dataset/) and unzip to $FACTNERF_ROOT
## Acknowledgement and Licenses
Some codes are adapted from the awesome repositories: [NiceSlam](
https://github.com/cvg/nice-slam) and [Neural Scene Graphs](https://github.com/princeton-computational-imaging/neural-scene-graphs). We appreciated their efforts in open-sourcing their implementation. We also thank the authors of [DeformingThings4D](https://github.com/rabbityl/DeformingThings4D) for allowing us to upload our synthetic dataset. Please be aware of all corresponding licenses.
## Citation
````
@misc{wong2023factored,
title={Factored Neural Representation for Scene Understanding},
author={Yu-Shiang Wong and Niloy J. Mitra},
year={2023},
eprint={2304.10950},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
````