Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/zju3dv/object_nerf
Code for "Learning Object-Compositional Neural Radiance Field for Editable Scene Rendering", ICCV 2021
https://github.com/zju3dv/object_nerf
3d-reconstruction 3d-vision nerf
Last synced: about 22 hours ago
JSON representation
Code for "Learning Object-Compositional Neural Radiance Field for Editable Scene Rendering", ICCV 2021
- Host: GitHub
- URL: https://github.com/zju3dv/object_nerf
- Owner: zju3dv
- License: mit
- Created: 2021-08-30T08:43:00.000Z (about 3 years ago)
- Default Branch: main
- Last Pushed: 2023-11-07T02:37:41.000Z (about 1 year ago)
- Last Synced: 2024-07-22T23:51:18.099Z (4 months ago)
- Topics: 3d-reconstruction, 3d-vision, nerf
- Language: Python
- Homepage: https://zju3dv.github.io/object_nerf/
- Size: 6.76 MB
- Stars: 313
- Watchers: 31
- Forks: 23
- Open Issues: 13
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-NeRF - Torch - Compositional Neural Radiance Field for Editable Scene Rendering](https://openaccess.thecvf.com/content/ICCV2021/papers/Yang_Learning_Object-Compositional_Neural_Radiance_Field_for_Editable_Scene_Rendering_ICCV_2021_paper.pdf)|[Project Page](https://zju3dv.github.io/object_nerf/)| (Papers / NeRF Related Tasks)
- awesome-NeRF - Torch - Compositional Neural Radiance Field for Editable Scene Rendering](https://openaccess.thecvf.com/content/ICCV2021/papers/Yang_Learning_Object-Compositional_Neural_Radiance_Field_for_Editable_Scene_Rendering_ICCV_2021_paper.pdf)|[Project Page](https://zju3dv.github.io/object_nerf/)| (Papers / NeRF Related Tasks)
README
# Learning Object-Compositional Neural Radiance Field for Editable Scene Rendering
### [Project Page](https://zju3dv.github.io/object_nerf) | [Video](https://www.youtube.com/watch?v=VTEROu-Yz04) | [Paper](http://www.cad.zju.edu.cn/home/gfzhang/papers/object_nerf/object_nerf.pdf)
> [Learning Object-Compositional Neural Radiance Field for Editable Scene Rendering](http://www.cad.zju.edu.cn/home/gfzhang/papers/object_nerf/object_nerf.pdf)
> Bangbang Yang, Yinda Zhang, Yinghao Xu, Yijin Li, Han Zhou, Hujun Bao, Guofeng Zhang, Zhaopeng Cui.
> ICCV 2021
## Installation
We have tested the code on pytorch 1.8.1, while a newer version of pytorch should also work.
```bash
conda create -n object_nerf python=3.8
conda activate object_nerf
conda install pytorch==1.8.1 torchvision cudatoolkit=11.1 -c pytorch -c conda-forge
pip install -r requirements.txt
```
## Data Preparation
Please go to the [data preparation][1].
## Training
You can run `train.py` to train the model, and here are two examples.
```bash
# train on ScanNet 0113
python train.py dataset_config=config/scannet_base_0113_multi.yml "img_wh=[640,480]" exp_name=my_expr_scannet_0113
# train on ToyDesk 2
python train.py dataset_config=config/toy_desk_2.yml "img_wh=[640,480]" exp_name=my_expr_toydesk_2
```
## Editable Scene Rendering
Here we provide two examples of scene editing with pre-trained models ([download link](https://www.dropbox.com/scl/fi/kz5r1y3pct8uvzmog22hl/object_nerf_edit_demo_models.zip?rlkey=e06i0y3m3uwocnxk0wrf10m62&dl=0)).
### ScanNet Object Duplicating and Moving
```bash
python test/demo_editable_render.py \
config=test/config/edit_scannet_0113.yaml \
ckpt_path=../object_nerf_edit_demo_models/scannet_0113/last.ckpt \
prefix=scannet_0113_duplicating_moving
```
### ToyDesk Object Rotating
```bash
python test/demo_editable_render.py \
config=test/config/edit_toy_desk_2.yaml \
ckpt_path=../object_nerf_edit_demo_models/toydesk_2/last.ckpt \
prefix=toy_desk2_rotating
```
Remember to change the `ckpt_path` to the uncompressed model checkpoint file.
You can find the rendered image in `debug/rendered_view/render_xxxxxx_scannet_0113_duplicating_moving` or `debug/rendered_view/render_xxxxxx_toy_desk2_rotating` which should look as follows:
    
## Citation
If you find this work useful, please consider citing:
```
@inproceedings{yang2021objectnerf,
title={Learning Object-Compositional Neural Radiance Field for Editable Scene Rendering},
author={Yang, Bangbang and Zhang, Yinda and Xu, Yinghao and Li, Yijin and Zhou, Han and Bao, Hujun and Zhang, Guofeng and Cui, Zhaopeng},
booktitle = {International Conference on Computer Vision ({ICCV})},
month = {October},
year = {2021},
}
```
## Acknowledgement
In this project we use (parts of) the implementations of the following works:
- [nerf_pl](https://github.com/kwea123/nerf_pl/) by kwea123.
- [nerf_pytorch](https://github.com/yenchenlin/nerf-pytorch) by Yen-Chen Lin.
- [scannet](https://github.com/ScanNet/ScanNet) by Angela Dai.
We thank the respective authors for open sourcing their methods.
[1]: ./data_preparation/