“Relighting Neural Radiance Fields with Shadow and Highlight Hints” by Zeng, Chen, Dong, Peers, Wu, et al. …




    Relighting Neural Radiance Fields with Shadow and Highlight Hints

Session/Category Title: Environmental Rendering: NeRFs On Earth




    This paper presents a novel neural implicit radiance representation for free viewpoint relighting from a small set of unstructured photographs of an object lit by a moving point light source different from the view position. We express the shape as a signed distance function modeled by a multi layer perceptron. In contrast to prior relightable implicit neural representations, we do not disentangle the different light transport components, but model both the local and global light transport at each point by a second multi layer perceptron that, in addition, to density features, the current position, the normal (from the signed distance function), view direction, and light position, also takes shadow and highlight hints to aid the network in modeling the corresponding high frequency light transport effects. These hints are provided as a suggestion, and we leave it up to the network to decide how to incorporate these in the final relit result. We demonstrate and validate our neural implicit representation on synthetic and real scenes exhibiting a wide variety of shapes, material properties, and global illumination light transport.


    1. Mojtaba Bemana, Karol Myszkowski, Hans-Peter Seidel, and Tobias Ritschel. 2020. X-Fields: Implicit Neural View-, Light- and Time-Image Interpolation. ACM Trans. Graph. 39, 6 (2020).
    2. Sai Bi, Stephen Lombardi, Shunsuke Saito, Tomas Simon, Shih-En Wei, Kevyn Mcphail, Ravi Ramamoorthi, Yaser Sheikh, and Jason Saragih. 2021. Deep relightable appearance models for animatable faces. ACM Trans. Graph. 40, 4 (2021), 1–15.
    3. Sai Bi, Zexiang Xu, Kalyan Sunkavalli, Miloš Hašan, Yannick Hold-Geoffroy, David Kriegman, and Ravi Ramamoorthi. 2020. Deep Reflectance Volumes: Relightable Reconstructions from Multi-View Photometric Images. In ECCV. 294–311.
    4. Mark Boss, Raphael Braun, Varun Jampani, Jonathan T. Barron, Ce Liu, and Hendrik P.A. Lensch. 2021a. NeRD: Neural Reflectance Decomposition from Image Collections. In ICCV.
    5. Mark Boss, Andreas Engelhardt, Abhishek Kar, Yuanzhen Li, Deqing Sun, Jonathan T. Barron, Hendrik P.A. Lensch, and Varun Jampani. 2022. SAMURAI: Shape And Material from Unconstrained Real-world Arbitrary Image collections. In NeurIPS.
    6. Mark Boss, Varun Jampani, Raphael Braun, Ce Liu, Jonathan Barron, and Hendrik PA Lensch. 2021b. Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decomposition. In NeurIPS, Vol. 34. 10691–10704.
    7. Guangyan Cai, Kai Yan, Zhao Dong, Ioannis Gkioulekas, and Shuang Zhao. 2022. Physics-Based Inverse Rendering using Combined Implicit and Explicit Geometries. Comp. Graph. Forum 41, 4 (2022), 129–138.
    8. Wenzheng Chen, Joey Litalien, Jun Gao, Zian Wang, Clement Fuji Tsang, Sameh Khalis, Or Litany, and Sanja Fidler. 2021. DIB-R++: Learning to Predict Lighting and Material with a Hybrid Differentiable Renderer. In NeurIPS.
    9. Paul Debevec, Tim Hawkins, Chris Tchou, Haarm-Pieter Duiker, Westley Sarokin, and Mark Sagar. 2000. Acquiring the Reflectance Field of a Human Face. In Proceedings of the 27th Annual Conference on Computer Graphics and Interactive Techniques. 145–156.
    10. Yue Dong. 2019. Deep appearance modeling: A survey. Visual Informatics 3, 2 (2019), 59–68.
    11. Farshad Einabadi, Jean-Yves Guillemaut, and Adrian Hilton. 2021. Deep neural models for illumination estimation and relighting: A survey. In Comp. Graph. Forum, Vol. 40. 315–331.
    12. Duan Gao, Guojun Chen, Yue Dong, Pieter Peers, Kun Xu, and Xin Tong. 2020. Deferred Neural Lighting: Free-Viewpoint Relighting from Unstructured Photographs. ACM Trans. Graph. 39, 6, Article 258 (nov 2020).
    13. David Griffiths, Tobias Ritschel, and Julien Philip. 2022. OutCast: Outdoor Single-image Relighting with Cast Shadows. Comp. Graph. Forum 41, 2 (2022), 179–193.
    14. Amos Gropp, Lior Yariv, Niv Haim, Matan Atzmon, and Yaron Lipman. 2020. Implicit geometric regularization for learning shapes. arXiv preprint arXiv:2002.10099 (2020).
    15. Kaiwen Guo, Peter Lincoln, Philip Davidson, Jay Busch, Xueming Yu, Matt Whalen, Geoff Harvey, Sergio Orts-Escolano, Rohit Pandey, Jason Dourgarian, Danhang Tang, Anastasia Tkach, Adarsh Kowdle, Emily Cooper, Mingsong Dou, Sean Fanello, Graham Fyffe, Christoph Rhemann, Jonathan Taylor, Paul Debevec, and Shahram Izadi. 2019. The Relightables: Volumetric Performance Capture of Humans with Realistic Relighting. ACM Trans. Graph. 38, 6, Article 217 (nov 2019).
    16. Jon Hasselgren, Nikolai Hofmann, and Jacob Munkberg. 2022. Shape, Light, and Material Decomposition from Images using Monte Carlo Rendering and Denoising. In NeurIPS.
    17. Yoshihiro Kanamori and Yuki Endo. 2018. Relighting Humans: Occlusion-Aware Inverse Rendering for Full-Body Human Images. ACM Trans. Graph. 37, 6, Article 270 (Dec. 2018).
    18. Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In ICLR.
    19. Zhengfei Kuang, Kyle Olszewski, Menglei Chai, Zeng Huang, Panos Achlioptas, and Sergey Tulyakov. 2022. NeROIC: Neural Rendering of Objects from Online Image Collections. ACM Trans. Graph. 41, 4, Article 56 (jul 2022).
    20. Quewei Li, Jie Guo, Yang Fei, Feichao Li, and Yanwen Guo. 2022. NeuLighting: Neural Lighting for Free Viewpoint Outdoor Scene Relighting with Unconstrained Photo Collections. In SIGGRAPH Asia 2022 Conference Papers. Article 13.
    21. Tzu-Mao Li, Miika Aittala, Frédo Durand, and Jaakko Lehtinen. 2018. Differentiable Monte Carlo Ray Tracing through Edge Sampling. ACM Trans. Graph. 37, 6, Article 222 (dec 2018).
    22. Matthew M. Loper and Michael J. Black. 2014. OpenDR: An Approximate Differentiable Renderer. In ECCV. 154–169.
    23. Fujun Luan, Shuang Zhao, Kavita Bala, and Zhao Dong. 2021. Unified Shape and SVBRDF Recovery using Differentiable Monte Carlo Rendering. Comp. Graph. Forum 40, 4 (2021), 101–113.
    24. Linjie Lyu, Ayush Tewari, Thomas Leimkühler, Marc Habermann, and Christian Theobalt. 2022. Neural Radiance Transfer Fields for Relightable Novel-View Synthesis with Global Illumination. In ECCV, Vol. 13677. 153–169.
    25. Ricardo Martin-Brualla, Noha Radwan, Mehdi S. M. Sajjadi, Jonathan T. Barron, Alexey Dosovitskiy, and Daniel Duckworth. 2021. NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections. In CVPR.
    26. Abhimitra Meka, Christian Häne, Rohit Pandey, Michael Zollhöfer, Sean Fanello, Graham Fyffe, Adarsh Kowdle, Xueming Yu, Jay Busch, Jason Dourgarian, Peter Denny, Sofien Bouaziz, Peter Lincoln, Matt Whalen, Geoff Harvey, Jonathan Taylor, Shahram Izadi, Andrea Tagliasacchi, Paul Debevec, Christian Theobalt, Julien Valentin, and Christoph Rhemann. 2019. Deep Reflectance Fields: High-Quality Facial Reflectance Field Inference from Color Gradient Illumination. ACM Trans. Graph. 38, 4, Article 77 (jul 2019).
    27. Abhimitra Meka, Rohit Pandey, Christian Haene, Sergio Orts-Escolano, Peter Barnum, Philip David-Son, Daniel Erickson, Yinda Zhang, Jonathan Taylor, Sofien Bouaziz, 2020. Deep relightable textures: volumetric performance capture with neural rendering. ACM Trans. Graph. 39, 6 (2020), 1–21.
    28. Moustafa Mahmoud Meshry, Dan B Goldman, Sameh Khamis, Hugues Hoppe, Rohit Kumar Pandey, Noah Snavely, and Ricardo Martin Brualla. 2019. Neural Rerendering in the Wild. In CVPR.
    29. 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. ECCV (2020).
    30. J. Munkberg, W. Chen, J. Hasselgren, A. Evans, T. Shen, T. Muller, J. Gao, and S. Fidler. 2022. Extracting Triangular 3D Models, Materials, and Lighting From Images. In CVPR. 8270–8280.
    31. O. Nalbach, E. Arabadzhiyska, D. Mehta, H.-P. Seidel, and T. Ritschel. 2017. Deep Shading: Convolutional Neural Networks for Screen Space Shading. Comp. Graph. Forum 36, 4 (2017), 65–78.
    32. Giljoo Nam, Joo Ho Lee, Diego Gutierrez, and Min H. Kim. 2018. Practical SVBRDF Acquisition of 3D Objects with Unstructured Flash Photography. ACM Trans. Graph. 37, 6, Article 267 (Dec. 2018).
    33. Merlin Nimier-David, Delio Vicini, Tizian Zeltner, and Wenzel Jakob. 2019. Mitsuba 2: A Retargetable Forward and Inverse Renderer. ACM Trans. Graph. 38, 6, Article 203 (nov 2019).
    34. Rohit Pandey, Sergio Orts Escolano, Chloe Legendre, Christian Haene, Sofien Bouaziz, Christoph Rhemann, Paul Debevec, and Sean Fanello. 2021. Total relighting: learning to relight portraits for background replacement. ACM Trans. Graph. 40, 4 (2021), 1–21.
    35. Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Kopf, Edward Yang, Zachary DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. PyTorch: An Imperative Style, High-Performance Deep Learning Library. In NeurIPS. 8024–8035.
    36. Julien Philip, Michaël Gharbi, Tinghui Zhou, Alexei A. Efros, and George Drettakis. 2019. Multi-view Relighting Using a Geometry-aware Network. ACM Trans. Graph. 38, 4, Article 78 (July 2019).
    37. Julien Philip, Sébastien Morgenthaler, Michaël Gharbi, and George Drettakis. 2021. Free-Viewpoint Indoor Neural Relighting from Multi-View Stereo. ACM Trans. Graph. 40, 5, Article 194 (sep 2021).
    38. Peiran Ren, Yue Dong, Stephen Lin, Xin Tong, and Baining Guo. 2015. Image Based Relighting Using Neural Networks. ACM Trans. Graph. 34, 4, Article 111 (jul 2015).
    39. Viktor Rudnev, Mohamed Elgharib, William Smith, Lingjie Liu, Vladislav Golyanik, and Christian Theobalt. 2022. NeRF for Outdoor Scene Relighting. In ECCV.
    40. Johannes Lutz Schönberger and Jan-Michael Frahm. 2016. Structure-from-Motion Revisited. In CVPR.
    41. P. P. Srinivasan, B. Deng, X. Zhang, M. Tancik, B. Mildenhall, and J. T. Barron. 2021. NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesis. In CVPR.
    42. Tiancheng Sun, Jonathan T. Barron, Yun-Ta Tsai, Zexiang Xu, Xueming Yu, Graham Fyffe, Christoph Rhemann, Jay Busch, Paul E. Debevec, and Ravi Ramamoorthi. 2019. Single image portrait relighting. ACM Trans. Graph. 38, 4, Article 79 (2019).
    43. Tiancheng Sun, Kai-En Lin, Sai Bi, Zexiang Xu, and Ravi Ramamoorthi. 2021. NeLF: Neural Light-transport Field for Portrait View Synthesis and Relighting. In EGSR. 155–166.
    44. Tiancheng Sun, Zexiang Xu, Xiuming Zhang, Sean Fanello, Christoph Rhemann, Paul Debevec, Yun-Ta Tsai, Jonathan T Barron, and Ravi Ramamoorthi. 2020. Light stage super-resolution: continuous high-frequency relighting. ACM Trans. Graph. 39, 6 (2020), 1–12.
    45. Ayush Tewari, Justus Thies, Ben Mildenhall, Pratul Srinivasan, Edgar Tretschk, W Yifan, Christoph Lassner, Vincent Sitzmann, Ricardo Martin-Brualla, Stephen Lombardi, 2022. Advances in neural rendering. In Comp. Graph. Forum, Vol. 41. 703–735.
    46. Dor Verbin, Peter Hedman, Ben Mildenhall, Todd Zickler, Jonathan T Barron, and Pratul P Srinivasan. 2022. Ref-nerf: Structured view-dependent appearance for neural radiance fields. In CVPR. 5481–5490.
    47. Bruce Walter, Stephen R Marschner, Hongsong Li, and Kenneth E Torrance. 2007. Microfacet models for refraction through rough surfaces. In EGSR. 195–206.
    48. 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. NeurIPS (2021).
    49. Jiankai Xing, Fujun Luan, Ling-Qi Yan, Xuejun Hu, Houde Qian, and Kun Xu. 2022. Differentiable Rendering Using RGBXY Derivatives and Optimal Transport. ACM Trans. Graph. 41, 6, Article 189 (nov 2022).
    50. Zexiang Xu, Kalyan Sunkavalli, Sunil Hadap, and Ravi Ramamoorthi. 2018. Deep Image-based Relighting from Optimal Sparse Samples. ACM Trans. Graph. 37, 4, Article 126 (July 2018).
    51. Wenqi Yang, Guanying Chen, Chaofeng Chen, Zhenfang Chen, and Kwan-Yee K. Wong. 2022. PS-NeRF: Neural Inverse Rendering for Multi-view Photometric Stereo. In ECCV.
    52. Yao Yao, Jingyang Zhang, Jingbo Liu, Yihang Qu, Tian Fang, David McKinnon, Yanghai Tsin, and Long Quan. 2022. NeILF: Neural Incident Light Field for Material and Lighting Estimation. In ECCV.
    53. Yu-Ying Yeh, Koki Nagano, Sameh Khamis, Jan Kautz, Ming-Yu Liu, and Ting-Chun Wang. 2022. Learning to Relight Portrait Images via a Virtual Light Stage and Synthetic-to-Real Adaptation. ACM Trans. Graph. 41, 6 (2022), 1–21.
    54. Kai Zhang, Fujun Luan, Zhengqi Li, and Noah Snavely. 2022a. IRON: Inverse Rendering by Optimizing Neural SDFs and Materials from Photometric Images. In CVPR. 5555–5564.
    55. Kai Zhang, Fujun Luan, Qianqian Wang, Kavita Bala, and Noah Snavely. 2021b. PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relighting. In CVPR.
    56. 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.
    57. Xiuming Zhang, Sean Fanello, Yun-Ta Tsai, Tiancheng Sun, Tianfan Xue, Rohit Pandey, Sergio Orts-Escolano, Philip Davidson, Christoph Rhemann, Paul Debevec, Jonathan T. Barron, Ravi Ramamoorthi, and William T. Freeman. 2021a. Neural Light Transport for Relighting and View Synthesis. ACM Trans. Graph. 40, 1, Article 9 (jan 2021).
    58. Xiuming Zhang, Pratul P. Srinivasan, Boyang Deng, Paul Debevec, William T. Freeman, and Jonathan T. Barron. 2021c. NeRFactor: Neural Factorization of Shape and Reflectance under an Unknown Illumination. ACM Trans. Graph. 40, 6, Article 237 (dec 2021).
    59. Yuanqing Zhang, Jiaming Sun, Xingyi He, Huan Fu, Rongfei Jia, and Xiaowei Zhou. 2022b. Modeling Indirect Illumination for Inverse Rendering. In CVPR.
    60. Quan Zheng, Gurprit Singh, and Hans-Peter Seidel. 2021. Neural Relightable Participating Media Rendering. In NeurIPS, Vol. 34. 15203–15215.

ACM Digital Library Publication:

Overview Page: