paper-with-me

홈 › Papers

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

2022-12-06 · CVPR 2023 1 · Yuechen Zhang, Zexin He, Jinbo Xing, Xufeng Yao, Jiaya Jia

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.

📄 PDF Abstract BibTeX arXiv:2212.02766

Code (1)

dvlab-research/ref-npr 공식 구현 pytorch

Tasks

Semantic correspondence

Similar Papers 제목 키워드 기반

FPRF: Feed-Forward Photorealistic Style Transfer of Large-Scale 3D Neural Radiance Fields

2024-01-10 · GeonU Kim, Kim Youwang, Tae-Hyun Oh

We present FPRF, a feed-forward photorealistic style transfer method for large-scale 3D neural radiance fields. FPRF stylizes large-scale 3D scenes with arbitrary, multiple style reference images without additional optim…

Semantic correspondenceStyle Transfer

SIGNeRF: Scene Integrated Generation for Neural Radiance Fields

2024-01-03 · CVPR 2024 1 · Jan-Niklas Dihlmann, Andreas Engelhardt, Hendrik Lensch

Advances in image diffusion models have recently led to notable improvements in the generation of high-quality images. In combination with Neural Radiance Fields (NeRFs), they enabled new opportunities in 3D generation. …

3D GenerationNeRF

FLAME-in-NeRF : Neural control of Radiance Fields for Free View Face Animation

2021-08-10 · ShahRukh Athar, Zhixin Shu, Dimitris Samaras

This paper presents a neural rendering method for controllable portrait video synthesis. Recent advances in volumetric neural rendering, such as neural radiance fields (NeRF), has enabled the photorealistic novel view sy…

Face ModelNeRFNeural RenderingNovel View Synthesis

FLAME-in-NeRF: Neural control of Radiance Fields for Free View Face Animation

2021-09-29 · ShahRukh Athar, Zhixin Shu, Dimitris Samaras

This paper presents a neural rendering method for controllable portrait video synthesis.Recent advances in volumetric neural rendering, such as neural radiance fields (NeRF), have enabled the photorealistic novel view sy…

NeRFNeural RenderingNovel View Synthesis

MERF: Memory-Efficient Radiance Fields for Real-time View Synthesis in Unbounded Scenes

2023-02-23 · Christian Reiser, Richard Szeliski, Dor Verbin, Pratul P. Srinivasan 외

Neural radiance fields enable state-of-the-art photorealistic view synthesis. However, existing radiance field representations are either too compute-intensive for real-time rendering or require too much memory to scale …