https://github.com/lwwu2/diver-rt
Real-time application of DIVeR
https://github.com/lwwu2/diver-rt
Last synced: 29 days ago
JSON representation
Real-time application of DIVeR
- Host: GitHub
- URL: https://github.com/lwwu2/diver-rt
- Owner: lwwu2
- Created: 2021-11-16T06:39:33.000Z (over 3 years ago)
- Default Branch: main
- Last Pushed: 2021-11-23T01:09:39.000Z (over 3 years ago)
- Last Synced: 2024-11-07T03:31:09.665Z (6 months ago)
- Language: C
- Size: 26.4 KB
- Stars: 59
- Watchers: 4
- Forks: 8
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- awesome-NeRF - Torch - time and Accurate Neural Radiance Fields with Deterministic Integration for Volume Rendering](https://openaccess.thecvf.com/content/CVPR2022/papers/Wu_DIVeR_Real-Time_and_Accurate_Neural_Radiance_Fields_With_Deterministic_Integration_CVPR_2022_paper.pdf)| (Papers / NeRF Related Tasks)
- awesome-NeRF - Torch - time and Accurate Neural Radiance Fields with Deterministic Integration for Volume Rendering](https://openaccess.thecvf.com/content/CVPR2022/papers/Wu_DIVeR_Real-Time_and_Accurate_Neural_Radiance_Fields_With_Deterministic_Integration_CVPR_2022_paper.pdf)| (Papers / NeRF Related Tasks)
README
# DIVeR: Real-time CUDA Application
This repo contains the code for the real-time application of DIVeR implemented in Python+CUDA.
## Setup
- python 3.8
- pytorch 1.9.0
- moderngl
- moderngl-window
### Pre-trained model
We have two versions of pre-trained models trained on nerf_synthetic dataset.
- Our [256 model](https://drive.google.com/file/d/1dEpMamHreZVtKV9BZA9uGFUJKQbBdJFq/view?usp=sharing) (256x256x256 voxel grid).
- Our [128 model](https://drive.google.com/file/d/11p0XdSNQrp_9HDbvQZaS7s9LZDi_v3QH/view?usp=sharing) (128x128x128 voxel grid).
The 128 model runs much faster with smaller storage cost, but the 256 model has better rendering quality.
## Usage
To launch the real-time application, run:
```shell
python run.py --weight_path=PATH_TO_WEIGHT_FILE \
--voxel_num=VOXEL_GRID_SIZE \
--device=GPU_DEVICE
```
## Resources
- [Project page](https://lwwu2.github.io/diver)
- [Paper](https://arxiv.org/abs/2111.10427)
- [Training code](https://github.com/lwwu2/diver)
## Citation
```
@misc{wu2021diver,
title={DIVeR: Real-time and Accurate Neural Radiance Fields with Deterministic Integration for Volume Rendering},
author={Liwen Wu and Jae Yong Lee and Anand Bhattad and Yuxiong Wang and David Forsyth},
year={2021},
eprint={2111.10427},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
```