Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/phuang1024/nerf
Implementation of Neural Radiance Fields.
https://github.com/phuang1024/nerf
Last synced: 9 days ago
JSON representation
Implementation of Neural Radiance Fields.
- Host: GitHub
- URL: https://github.com/phuang1024/nerf
- Owner: phuang1024
- License: mit
- Created: 2023-05-16T16:18:09.000Z (over 1 year ago)
- Default Branch: master
- Last Pushed: 2023-05-28T00:36:46.000Z (over 1 year ago)
- Last Synced: 2024-11-05T22:37:52.618Z (about 2 months ago)
- Language: Python
- Size: 178 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# NeRF
Implementation of Neural Radiance Fields.
Original paper: https://arxiv.org/abs/2003.08934
## Results
Top is NeRF render. Bottom is ground truth.
5000 iters:
![](https://github.com/phuang1024/NeRF/blob/master/examples/duck.jpg?raw=true)
1400 iters:
![](https://github.com/phuang1024/NeRF/blob/master/examples/plant.jpg?raw=true)
In theory, the quality should improve with more training. The paper states that 100k to 300k
iterations are needed for a good result. However, with my slow code, it takes too long.