https://github.com/Kai-46/ARF-svox2

Artistic Radiance Fields
https://github.com/Kai-46/ARF-svox2

Last synced: about 1 month ago
JSON representation

Artistic Radiance Fields

• Host: GitHub
• URL: https://github.com/Kai-46/ARF-svox2
• Owner: Kai-46
• License: bsd-2-clause
• Created: 2022-06-13T20:41:20.000Z (over 2 years ago)
• Default Branch: master
• Last Pushed: 2022-07-22T12:31:40.000Z (over 2 years ago)
• Last Synced: 2023-11-07T17:19:40.184Z (about 1 year ago)
• Language: Python
• Size: 6.98 MB
• Stars: 454
• Watchers: 17
• Forks: 41
• Open Issues: 11
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-NeRF - Torch
• awesome-NeRF - Torch

README

        
# ARF: Artistic Radiance Fields

Project page: 

![](./resources/ARF.mov)

Citation:

```

@misc{zhang2022arf,

      title={ARF: Artistic Radiance Fields}, 

      author={Kai Zhang and Nick Kolkin and Sai Bi and Fujun Luan and Zexiang Xu and Eli Shechtman and Noah Snavely},

      year={2022},

      booktitle={ECCV},

}

```

## Quick start

### Install environment

```bash

. ./create_env.sh

```

### Download data

```bash

. ./download_data.sh

```

### Optimize artistic radiance fields

```bash

cd opt && . ./try_{llff/tnt/custom}.sh [scene_name] [style_id]

```

* Select ```{llff/tnt/custom}``` according to your data type. For example, use ```llff``` for ```flower``` scene, ```tnt``` for ```Playground``` scene, and ```custom``` for ```lego``` scene. 

* ```[style_id].jpg``` is the style image inside ```./data/styles```. For example, ```14.jpg``` is the starry night painting.

* Note that a photorealistic radiance field will first be reconstructed for each scene, if it doesn't exist on disk. This will take extra time.

### Check results

The optimized artistic radiance field is inside ```opt/ckpt_arf/[scene_name]_[style_id]```, while the photorealistic one is inside ```opt/ckpt_svox2/[scene_name]```.

### Custom data

Please follow the steps on [Plenoxel](https://github.com/sxyu/svox2)  to prepare your own custom data.

## ARF with other NeRF variants

* [ARF-TensoRF](): to be released; stay tuned.

* [ARF-NeRF](): to be released; stay tuned.

## Acknowledgement:

We would like to thank [Plenoxel](https://github.com/sxyu/svox2) authors for open-sourcing their implementations.