Ref-NPR: Reference-Based Non-Photorealistic Radiance Fields for Controllable Scene Stylization
Yuechen Zhang, Zexin He, Jinbo Xing, Xufeng Yao, Jiaya Jia
摘要
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-NP R) 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 out-performs 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.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper14
- Real-World Image Variation by Aligning Diffusion Inversion ChainYuechen Zhang, Jinbo Xing, Eric Lo, Jiaya JiaNeurIPS 2023 · 被引用 56 次
- 3Doodle: Compact Abstraction of Objects with 3D StrokesChangwoon Choi, Jaeah Lee, Jaesik Park, Young Min KimSIGGRAPH 2024 · 被引用 12 次
- MS-GS: Multi-Appearance Sparse-View 3D Gaussian Splatting in the WildDeming Li, Kaiwen Jiang, Yutao Tang, Ravi Ramamoorthi 等NeurIPS 2025 · 被引用 7 次
- LAENeRF: Local Appearance Editing for Neural Radiance FieldsLukas Radl, Michael Steiner, Andreas Kurz, Markus SteinbergerCVPR 2024 · 被引用 6 次
- Multi-StyleGS: Stylized Gaussian Splatting with Multiple StylesYangkai Lin, Jiabao Lei, Kui JiaAAAI 2025 · 被引用 5 次
它引用的顶会 Paper13
- Adding Conditional Control to Text-to-Image Diffusion ModelsLvmin Zhang, Anyi Rao, Maneesh AgrawalaICCV 2023 · 被引用 6,759 次
- Instant neural graphics primitives with a multiresolution hash encodingThomas Müller, Alex Evans, Christoph Schied, Alexander KellerSIGGRAPH 2022 · 被引用 4,089 次
- Plenoxels: Radiance Fields without Neural NetworksSara Fridovich-Keil, Alex Yu, Matthew Tancik, Qinhong Chen 等CVPR 2022 · 被引用 1,237 次
- Depth-supervised NeRF: Fewer Views and Faster Training for FreeKangle Deng, Andrew Liu, Jun-Yan Zhu, Deva RamananCVPR 2022 · 被引用 756 次
- Block-NeRF: Scalable Large Scene Neural View SynthesisMatthew Tancik, Vincent Casser, Xinchen Yan, Sabeek Pradhan 等CVPR 2022 · 被引用 702 次
相关 Paper
- FPRF: Feed-Forward Photorealistic Style Transfer of Large-Scale 3D Neural Radiance FieldsGeonU Kim, Kim Youwang, Tae-Hyun OhAAAI 2024 · 被引用 12 次
- StylizedNeRF: Consistent 3D Scene Stylization as Stylized NeRF via 2D-3D Mutual LearningYihua Huang, Yue He, Yu-Jie Yuan, Yu-Kun Lai 等CVPR 2022 · 被引用 145 次
- Locally Stylized Neural Radiance FieldsHong-Wing Pang, Binh-Son Hua, Sai-Kit YeungICCV 2023 · 被引用 18 次
- Transforming Radiance Field with Lipschitz Network for Photorealistic 3D Scene StylizationZicheng Zhang, Yinglu Liu, Congying Han, Yingwei Pan 等CVPR 2023
- NeRF Analogies: Example-Based Visual Attribute Transfer for NeRFsMichael Fischer, Zhengqin Li, Thu Nguyen-Phuoc, Aljaz Bozic 等CVPR 2024
