Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://fanegg.github.io/UV-Volumes/
[CVPR 2023] UV Volumes for Real-time Rendering of Editable Free-view Human Performance
https://fanegg.github.io/UV-Volumes/
avatar nerf
Last synced: 3 months ago
JSON representation
[CVPR 2023] UV Volumes for Real-time Rendering of Editable Free-view Human Performance
- Host: GitHub
- URL: https://fanegg.github.io/UV-Volumes/
- Owner: fanegg
- License: mit
- Created: 2022-03-27T23:54:54.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2024-03-06T12:34:46.000Z (4 months ago)
- Last Synced: 2024-03-06T13:51:41.855Z (4 months ago)
- Topics: avatar, nerf
- Language: Python
- Homepage: https://fanegg.github.io/UV-Volumes
- Size: 52.4 MB
- Stars: 134
- Watchers: 21
- Forks: 8
- Open Issues: 4
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Lists
- awesome-NeRF - UV Volumes for Real-time Rendering of Editable Free-view Human Performance - Volumes) | [bibtex](citations/UV-Volumes.txt) <!---Chen22arxiv_uvvolumes--> (Papers)
- awesome-scene-representation - UV Volumes for Real-time Rendering of Editable Free-view Human Performance - Volumes) | [bibtex](./citations/uvvolumes.txt) (Uncategorized / Uncategorized)
- awesome-NeRF - UV Volumes for Real-time Rendering of Editable Free-view Human Performance - Volumes) | [bibtex](citations/UV-Volumes.txt) <!---Chen22arxiv_uvvolumes--> (Papers)
README
# UV Volumes for Real-time Rendering of Editable Free-view Human Performance
**[Project Page](https://fanegg.github.io/UV-Volumes) | [Paper](https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_UV_Volumes_for_Real-Time_Rendering_of_Editable_Free-View_Human_Performance_CVPR_2023_paper.pdf) | [Latest arXiv](https://arxiv.org/pdf/2203.14402.pdf) | [Supplementary](https://openaccess.thecvf.com/content/CVPR2023/supplemental/Chen_UV_Volumes_for_CVPR_2023_supplemental.pdf)**
> UV Volumes for Real-time Rendering of Editable Free-view Human Performance
> [Yue Chen*](https://scholar.google.com/citations?user=M2hq1_UAAAAJ&hl=en), [Xuan Wang*](https://scholar.google.com/citations?user=h-3xd3EAAAAJ&hl=en), [Xingyu Chen](https://scholar.google.com/citations?user=gDHPrWEAAAAJ&hl=en), [Qi Zhang](https://scholar.google.com/citations?user=2vFjhHMAAAAJ&hl=en), [Xiaoyu Li](https://scholar.google.com/citations?user=Dt0PcAYAAAAJ&hl=en), [Yu Guo†](https://scholar.google.com/citations?user=OemeiSIAAAAJ&hl=en), [Jue Wang](https://scholar.google.com/citations?user=Bt4uDWMAAAAJ&hl=en), [Fei Wang](https://scholar.google.com/citations?user=uU2JTpUAAAAJ&hl=en)
> (* equal contribution，† corresponding author)
> CVPR 2023
[](https://youtu.be/JftQnXLMmPc "UV Volumes for Real-time Rendering of Editable Free-view Human Performance")
This repository is an official implementation of [UV-Volumes](https://fanegg.github.io/UV-Volumes) using [pytorch](https://pytorch.org/).
## Installation
Please see [INSTALL.md](INSTALL.md) for manual installation.
## Run the code on ZJU-MoCap
Please see [INSTALL.md](INSTALL.md) to download the dataset.
### Training on ZJU-MoCap
Take the training on `sequence 313` as an example.
```
python3 train_net.py --cfg_file configs/zju_mocap_exp/313.yaml exp_name zju313 resume False output_depth True
```
You can monitor the training process by Tensorboard.
```
tensorboard --logdir data/record/UVvolume_ZJU
```
### Test on ZJU-MoCap
Take the test on `sequence 313` as an example.
```
python3 run.py --type evaluate --cfg_file configs/zju_mocap_exp/313.yaml exp_name zju313 use_lpips True test.frame_sampler_interval 1 use_nb_mask_at_box True save_img True T_threshold 0.75
```
## Run the code on CMU Panoptic
Please see [INSTALL.md](INSTALL.md) to download and process the dataset.
### Training on CMU Panoptic
Take the training on `171204_pose4_sample6` as an example.
```
python3 train_net.py --cfg_file configs/cmu_exp/p4s6.yaml exp_name p4s6 resume False output_depth True
```
You can monitor the training process by Tensorboard.
```
tensorboard --logdir data/record/UVvolume_CMU
```
### Test on CMU Panoptic
Take the test on `171204_pose4_sample6` as an example.
```
python3 run.py --type evaluate --cfg_file configs/cmu_exp/p4s6.yaml exp_name p4s6 use_lpips True test.frame_sampler_interval 1 use_nb_mask_at_box True save_img True
```
## Citation
If you find this code useful for your research, please use the following BibTeX entry.
```bibtex
@inproceedings{chen2023uv,
title={UV Volumes for real-time rendering of editable free-view human performance},
author={Chen, Yue and Wang, Xuan and Chen, Xingyu and Zhang, Qi and Li, Xiaoyu and Guo, Yu and Wang, Jue and Wang, Fei},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
pages={16621--16631},
year={2023}
}
```
## Acknowledge
Our code is based on the awesome pytorch implementation of [NeuralBody](https://github.com/zju3dv/neuralbody). We appreciate all the contributors.