“DE-NeRF: DEcoupled Neural Radiance Fields for View-Consistent Appearance Editing and High-Frequency Environmental Relighting” by Wu, Sun, Lai and Gao

  • ©Tong Wu, Jia-Mu Sun, Yu-Kun Lai, and Lin Gao




    DE-NeRF: DEcoupled Neural Radiance Fields for View-Consistent Appearance Editing and High-Frequency Environmental Relighting

Session/Category Title: Environmental Rendering: NeRFs On Earth




    Neural Radiance Fields (NeRF) have shown promising results in novel view synthesis. While achieving state-of-the-art rendering results, NeRF usually encodes all properties related to geometry and appearance of the scene together into several MLP (Multi-Layer Perceptron) networks, which hinders downstream manipulation of geometry, appearance and illumination. Recently researchers made attempts to edit geometry, appearance and lighting for NeRF. However, they fail to render view-consistent results after editing the appearance of the input scene. Moreover, high-frequency environmental relighting is also beyond their capability as lighting is modeled as Spherical Gaussian (SG) and Spherical Harmonic (SH) functions or a low-resolution environment map. To solve the above problems, we propose DE-NeRF to decouple view-independent appearance and view-dependent appearance in the scene with a hybrid lighting representation. Specifically, we first train a signed distance function to reconstruct an explicit mesh for the input scene. Then a decoupled NeRF learns to attach view-independent appearance to the reconstructed mesh by defining learnable disentangled features representing geometry and view-independent appearance on its vertices. For lighting, we approximate it with an explicit learnable environment map and an implicit lighting network to support both low-frequency and high-frequency relighting. By modifying the view-independent appearance, rendered results are consistent across different viewpoints. Our method also supports high-frequency environmental relighting by replacing the explicit environment map with a novel one and fitting the implicit lighting network to the novel environment map. Experiments show that our method achieves better editing and relighting performance both quantitatively and qualitatively compared to previous methods.


    1. Chong Bao, Bangbang Yang, Zeng Junyi, Bao Hujun, Zhang Yinda, Cui Zhaopeng, and Zhang Guofeng. 2022. NeuMesh: Learning Disentangled Neural Mesh-based Implicit Field for Geometry and Texture Editing. In ECCV. 597–614.
    2. Sai Bi, Zexiang Xu, Kalyan Sunkavalli, David J. Kriegman, and Ravi Ramamoorthi. 2020. Deep 3D Capture: Geometry and Reflectance From Sparse Multi-View Images. In CVPR. 5959–5968.
    3. Mark Boss, Raphael Braun, Varun Jampani, Jonathan T Barron, Ce Liu, and Hendrik Lensch. 2021a. NeRD: Neural reflectance decomposition from image collections. In ICCV. 12684–12694.
    4. Mark Boss, Varun Jampani, Raphael Braun, Ce Liu, Jonathan T. Barron, and Hendrik P.A. Lensch. 2021b. Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decomposition. In Advances in Neural Information Processing Systems. 10691–10704.
    5. Zhiqin Chen and Hao Zhang. 2019. Learning implicit fields for generative shape modeling. In CVPR. 5939–5948.
    6. Sara Fridovich-Keil, Alex Yu, Matthew Tancik, Qinhong Chen, Benjamin Recht, and Angjoo Kanazawa. 2022. Plenoxels: Radiance Fields Without Neural Networks. In CVPR. 5501–5510.
    7. Lin Gao, Tong Wu, Yu-Jie Yuan, Ming-Xian Lin, Yu-Kun Lai, and Hao Zhang. 2021. TM-NET: Deep Generative Networks for Textured Meshes. ACM Trans. Graph. 40, 6 (2021), 263:1–263:15.
    8. Lin Gao, Jie Yang, Tong Wu, Yu-Jie Yuan, Hongbo Fu, Yu-Kun Lai, and Hao Zhang. 2019. SDM-NET: deep generative network for structured deformable mesh. ACM Trans. Graph. 38, 6 (2019), 243:1–243:15.
    9. Stephan J Garbin, Marek Kowalski, Virginia Estellers, Stanislaw Szymanowicz, Shideh Rezaeifar, Jingjing Shen, Matthew Johnson, and Julien Valentin. 2022. VolTeMorph: Realtime, Controllable and Generalisable Animation of Volumetric Representations. arXiv:2208.00949 (2022).
    10. Jon Hasselgren, Nikolai Hofmann, and Jacob Munkberg. 2022. Shape, Light, and Material Decomposition from Images using Monte Carlo Rendering and Denoising. In Advances in Neural Information Processing Systems.
    11. Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium. In Advances in Neural Information Processing Systems. 6626–6637.
    12. Yi-Hua Huang, Yue He, Yu-Jie Yuan, Yu-Kun Lai, and Lin Gao. 2022. StylizedNeRF: consistent 3D scene stylization as stylized NeRF via 2D-3D mutual learning. In CVPR. 18342–18352.
    13. Rasmus Ramsbøl Jensen, Anders Lindbjerg Dahl, George Vogiatzis, Engin Tola, and Henrik Aanæs. 2014. Large Scale Multi-view Stereopsis Evaluation. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. 406–413.
    14. Brian Karis. 2013. Real Shading in Unreal Engine 4. (2013).
    15. Jaroslav Krivánek and Mark Colbert. 2008. Real-time Shading with Filtered Importance Sampling. Comput. Graph. Forum 27, 4 (2008), 1147–1154.
    16. Zhengfei Kuang, Kyle Olszewski, Menglei Chai, Zeng Huang, Panos Achlioptas, and Sergey Tulyakov. 2022. NeROIC: Neural Object Capture and Rendering from Online Image Collections. Computing Research Repository (CoRR) abs/2201.02533 (2022).
    17. Samuli Laine, Janne Hellsten, Tero Karras, Yeongho Seol, Jaakko Lehtinen, and Timo Aila. 2020. Modular Primitives for High-Performance Differentiable Rendering. ACM Trans. Graph. 39, 6 (2020), 194:1–194:14.
    18. Lingjie Liu, Jiatao Gu, Kyaw Zaw Lin, Tat-Seng Chua, and Christian Theobalt. 2020. Neural sparse voxel fields. Advances in Neural Information Processing Systems (2020), 15651–15663.
    19. Steven Liu, Xiuming Zhang, Zhoutong Zhang, Richard Zhang, Jun-Yan Zhu, and Bryan Russell. 2021. Editing conditional radiance fields. In ICCV. 5773–5783.
    20. Xiaoxiao Long, Cheng Lin, Peng Wang, Taku Komura, and Wenping Wang. 2022. SparseNeuS: Fast Generalizable Neural Surface Reconstruction from Sparse views. ECCV (2022), 210–227.
    21. William E. Lorensen and Harvey E. Cline. 1987. Marching cubes: A high resolution 3D surface construction algorithm. In Proceedings of the 14th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH. 163–169.
    22. Wojciech Matusik, Hanspeter Pfister, Matthew Brand, and Leonard McMillan. 2003. A data-driven reflectance model. ACM Trans. Graph. 22, 3 (2003), 759–769.
    23. Lars Mescheder, Michael Oechsle, Michael Niemeyer, Sebastian Nowozin, and Andreas Geiger. 2019. Occupancy networks: Learning 3d reconstruction in function space. In CVPR. 4460–4470.
    24. Ben Mildenhall, Pratul P Srinivasan, Matthew Tancik, Jonathan T Barron, Ravi Ramamoorthi, and Ren Ng. 2020. NeRF: Representing scenes as neural radiance fields for view synthesis. In ECCV. 405–421.
    25. Jacob Munkberg, Wenzheng Chen, Jon Hasselgren, Alex Evans, Tianchang Shen, Thomas Müller, Jun Gao, and Sanja Fidler. 2022. Extracting Triangular 3D Models, Materials, and Lighting From Images. In CVPR. 8270–8280.
    26. Michael Niemeyer, Lars Mescheder, Michael Oechsle, and Andreas Geiger. 2020. Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision. In CVPR. 3501–3512.
    27. Michael Oechsle, Lars M. Mescheder, Michael Niemeyer, Thilo Strauss, and Andreas Geiger. 2019. Texture Fields: Learning Texture Representations in Function Space. In ICCV. 4530–4539.
    28. Michael Oechsle, Songyou Peng, and Andreas Geiger. 2021. Unisurf: Unifying neural implicit surfaces and radiance fields for multi-view reconstruction. In ICCV. 5589–5599.
    29. Jeong Joon Park, Peter Florence, Julian Straub, Richard Newcombe, and Steven Lovegrove. 2019. Deepsdf: Learning continuous signed distance functions for shape representation. In CVPR. 165–174.
    30. Yicong Peng, Yichao Yan, Shenqi Liu, Yuhao Cheng, Shanyan Guan, Bowen Pan, Guangtao Zhai, and Xiaokang Yang. 2022. CageNeRF: Cage-based Neural Radiance Fields for Generalized 3D Deformation and Animation. In Advances in Neural Information Processing Systems.
    31. Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Björn Ommer. 2022. High-Resolution Image Synthesis With Latent Diffusion Models. In CVPR. 10684–10695.
    32. Tianchang Shen, Jun Gao, Kangxue Yin, Ming-Yu Liu, and Sanja Fidler. 2021. Deep marching tetrahedra: a hybrid representation for high-resolution 3d shape synthesis. In Advances in Neural Information Processing Systems. 6087–6101.
    33. Olga Sorkine-Hornung and Marc Alexa. 2007. As-rigid-as-possible surface modeling. In Symposium on Geometry Processing.
    34. Pratul P Srinivasan, Boyang Deng, Xiuming Zhang, Matthew Tancik, Ben Mildenhall, and Jonathan T Barron. 2021. NeRV: Neural reflectance and visibility fields for relighting and view synthesis. In CVPR. 7495–7504.
    35. Justus Thies, Michael Zollhöfer, and Matthias Nießner. 2019. Deferred neural rendering: image synthesis using neural textures. ACM Trans. Graph. 38, 4 (2019), 66:1–66:12.
    36. Dor Verbin, Peter Hedman, Ben Mildenhall, Todd E. Zickler, Jonathan T. Barron, and Pratul P. Srinivasan. 2022. Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fields. In CVPR. 5481–5490.
    37. Bruce Walter, Stephen R Marschner, Hongsong Li, and Kenneth E Torrance. 2007. Microfacet models for refraction through rough surfaces. In Eurographics conference on Rendering Techniques. 195–206.
    38. Can Wang, Ruixiang Jiang, Menglei Chai, Mingming He, Dongdong Chen, and Jing Liao. 2022. NeRF-Art: Text-Driven Neural Radiance Fields Stylization. arXiv:2212.08070 (2022).
    39. Jiaping Wang, Peiran Ren, Minmin Gong, John Snyder, and Baining Guo. 2009. All-frequency rendering of dynamic, spatially-varying reflectance. ACM Trans. Graph. 28, 5 (2009), 133.
    40. Miao Wang, Yu-Kun Lai, Yuan Liang, Ralph R. Martin, and Shi-Min Hu. 2014. BiggerPicture: data-driven image extrapolation using graph matching. ACM Trans. Graph. 33, 6 (2014), 173:1–173:13.
    41. Peng Wang, Lingjie Liu, Yuan Liu, Christian Theobalt, Taku Komura, and Wenping Wang. 2021. NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction. In Advances in Neural Information Processing Systems. 27171–27183.
    42. Zhou Wang, Alan C. Bovik, Hamid R. Sheikh, and Eero P. Simoncelli. 2004. Image Quality Assessment: From Error Visibility to Structural Similarity. IEEE Transactions on Image Processing 13, 4 (2004), 600–612.
    43. Tong Wu, Jiaqi Wang, Xingang Pan, Xudong Xu, Christian Theobalt, Ziwei Liu, and Dahua Lin. 2022. Voxurf: Voxel-based Efficient and Accurate Neural Surface Reconstruction. arXiv:2208.12697 (2022).
    44. Fanbo Xiang, Zexiang Xu, Milos Hasan, Yannick Hold-Geoffroy, Kalyan Sunkavalli, and Hao Su. 2021. Neutex: Neural texture mapping for volumetric neural rendering. In CVPR. 7119–7128.
    45. Qiangeng Xu, Zexiang Xu, Julien Philip, Sai Bi, Zhixin Shu, Kalyan Sunkavalli, and Ulrich Neumann. 2022. Point-nerf: Point-based neural radiance fields. In CVPR. 5438–5448.
    46. Tianhan Xu and Tatsuya Harada. 2022. Deforming Radiance Fields with Cages. In ECCV. 159–175.
    47. Lior Yariv, Jiatao Gu, Yoni Kasten, and Yaron Lipman. 2021. Volume Rendering of Neural Implicit Surfaces. In Advances in Neural Information Processing Systems. 4805–4815.
    48. Lior Yariv, Yoni Kasten, Dror Moran, Meirav Galun, Matan Atzmon, Ronen Basri, and Yaron Lipman. 2020. Multiview Neural Surface Reconstruction by Disentangling Geometry and Appearance. In Advances in Neural Information Processing Systems.
    49. Yu-Jie Yuan, Yang-Tian Sun, Yu-Kun Lai, Yuewen Ma, Rongfei Jia, and Lin Gao. 2022. NeRF-Editing: Geometry Editing of Neural Radiance Fields. In CVPR. 18332–18343.
    50. Jingyang Zhang, Yao Yao, and Long Quan. 2021c. Learning Signed Distance Field for Multi-View Surface Reconstruction. In ICCV. 6525–6534.
    51. Kai Zhang, Nick Kolkin, Sai Bi, Fujun Luan, Zexiang Xu, Eli Shechtman, and Noah Snavely. 2022a. ARF: Artistic Radiance Fields. In ECCV. 717–733.
    52. Kai Zhang, Fujun Luan, Qianqian Wang, Kavita Bala, and Noah Snavely. 2021a. PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relighting. In CVPR. 5453–5462.
    53. Richard Zhang, Phillip Isola, Alexei A Efros, Eli Shechtman, and Oliver Wang. 2018. The Unreasonable Effectiveness of Deep Features as a Perceptual Metric. In CVPR. 586–595.
    54. Xiuming Zhang, Pratul P Srinivasan, Boyang Deng, Paul Debevec, William T Freeman, and Jonathan T Barron. 2021b. NeRFactor: Neural factorization of shape and reflectance under an unknown illumination. ACM Trans. Graph. 40, 6 (2021), 1–18.
    55. Yuanqing Zhang, Jiaming Sun, Xingyi He, Huan Fu, Rongfei Jia, and Xiaowei Zhou. 2022b. Modeling Indirect Illumination for Inverse Rendering. In CVPR. 18622–18631.

ACM Digital Library Publication:

Overview Page: