ARF: Artistic Radiance Fields

July 22, 2022 ยท View on GitHub

Project page: https://www.cs.cornell.edu/projects/arf/

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

. ./create_env.sh

Download data

. ./download_data.sh

Optimize artistic radiance fields

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 to prepare your own custom data.

ARF with other NeRF variants

Acknowledgement:

We would like to thank Plenoxel authors for open-sourcing their implementations.