Ref-NPR: Reference-Based Non-Photorealistic Radiance Fields for Controllable Scene Stylization

Abstract

Current 3D scene stylization methods transfer textures and colors as styles using arbitrary style references, lacking meaningful semantic correspondences. We introduce Reference-Based Non-Photorealistic Radiance Fields (Ref-NPR) to address this limitation. This controllable method stylizes a 3D scene using radiance fields with a single stylized 2D view as a reference. We propose a ray registration process based on the stylized reference view to obtain pseudo-ray supervision in novel views. Then we exploit semantic correspondences in content images to fill occluded regions with perceptually similar styles, resulting in non-photorealistic and continuous novel view sequences. Our experimental results demonstrate that Ref-NPR outperforms existing scene and video stylization methods regarding visual quality and semantic correspondence. The code and data are publicly available on the project page at https://ref-npr.github.io.

Cite

Text

Zhang et al. "Ref-NPR: Reference-Based Non-Photorealistic Radiance Fields for Controllable Scene Stylization." Conference on Computer Vision and Pattern Recognition, 2023. doi:10.1109/CVPR52729.2023.00413

Markdown

[Zhang et al. "Ref-NPR: Reference-Based Non-Photorealistic Radiance Fields for Controllable Scene Stylization." Conference on Computer Vision and Pattern Recognition, 2023.](https://mlanthology.org/cvpr/2023/zhang2023cvpr-refnpr/) doi:10.1109/CVPR52729.2023.00413

BibTeX

@inproceedings{zhang2023cvpr-refnpr,
  title     = {{Ref-NPR: Reference-Based Non-Photorealistic Radiance Fields for Controllable Scene Stylization}},
  author    = {Zhang, Yuechen and He, Zexin and Xing, Jinbo and Yao, Xufeng and Jia, Jiaya},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2023},
  pages     = {4242-4251},
  doi       = {10.1109/CVPR52729.2023.00413},
  url       = {https://mlanthology.org/cvpr/2023/zhang2023cvpr-refnpr/}
}