https://github.com/autonomousvision/murf
[CVPR'24] MuRF: Multi-Baseline Radiance Fields
https://github.com/autonomousvision/murf
3d-context feed-forward-nerf large-baseline latent-volume multi-baseline small-baseline view-synthesis
Last synced: about 1 year ago
JSON representation
[CVPR'24] MuRF: Multi-Baseline Radiance Fields
- Host: GitHub
- URL: https://github.com/autonomousvision/murf
- Owner: autonomousvision
- License: mit
- Created: 2023-12-07T19:52:21.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2024-08-29T07:06:14.000Z (almost 2 years ago)
- Last Synced: 2025-04-01T18:23:07.198Z (over 1 year ago)
- Topics: 3d-context, feed-forward-nerf, large-baseline, latent-volume, multi-baseline, small-baseline, view-synthesis
- Language: Python
- Homepage: https://haofeixu.github.io/murf/
- Size: 159 KB
- Stars: 115
- Watchers: 7
- Forks: 6
- Open Issues: 5
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
MuRF: Multi-Baseline Radiance Fields
Haofei Xu
·
Anpei Chen
·
Yuedong Chen
·
Christos Sakaridis
·
Yulun Zhang
Marc Pollefeys
·
Andreas Geiger
·
Fisher Yu
CVPR 2024
Paper | Project Page
MuRF supports multiple different baseline settings.
MuRF achieves state-of-the-art performance under various evaluation settings.
## Installation
Our code is developed based on pytorch 1.10.1, CUDA 11.3 and python 3.8.
We recommend using [conda](https://www.anaconda.com/distribution/) for installation:
```
conda create -n murf python=3.8
conda activate murf
pip install -r requirements.txt
```
## Model Zoo
The models are hosted on Hugging Face 🤗 : https://huggingface.co/haofeixu/murf
Model details can be found at [MODEL_ZOO.md](MODEL_ZOO.md).
## Datasets
The datasets used to train and evaluate our models are detailed in [DATASETS.md](DATASETS.md)
## Evaluation
The evaluation scripts used to reproduce the numbers in our paper are detailed in [scripts/*_evaluate.sh](scripts).
## Rendering
The rendering scripts are detailed in [scripts/*_render.sh](scripts).
## Training
The training scripts are detailed in [scripts/*_train.sh](scripts).
## Citation
```
@inproceedings{xu2024murf,
title={MuRF: Multi-Baseline Radiance Fields},
author={Xu, Haofei and Chen, Anpei and Chen, Yuedong and Sakaridis, Christos and Zhang, Yulun and Pollefeys, Marc and Geiger, Andreas and Yu, Fisher},
booktitle={CVPR},
year={2024}
}
```
## Acknowledgements
This repo is heavily based on [MatchNeRF](https://github.com/donydchen/matchnerf), thanks [Yuedong Chen](https://donydchen.github.io/) for this fantastic work. This project also borrows code from several other repos: [GMFlow](https://github.com/haofeixu/gmflow), [UniMatch](https://github.com/autonomousvision/unimatch), [latent-diffusion](https://github.com/CompVis/latent-diffusion), [MVSNeRF](https://github.com/apchenstu/mvsnerf), [IBRNet](https://github.com/googleinterns/IBRNet), [ENeRF](https://github.com/zju3dv/ENeRF) and [cross_attention_renderer](https://github.com/yilundu/cross_attention_renderer). We thank the original authors for their excellent work.