“BakedSDF: Meshing Neural SDFs for Real-Time View Synthesis” by Yariv, Hedman, Reiser, Verbin, Srinivasan, et al. …

  • ©Lior Yariv, Peter Hedman, Christian Reiser, Dor Verbin, Pratul P. Srinivasan, Richard Szeliski, Jonathan T. Barron, and Ben Mildenhall




    BakedSDF: Meshing Neural SDFs for Real-Time View Synthesis

Session/Category Title: Neural Capturing




    We present a method for reconstructing high-quality meshes of large unbounded real-world scenes suitable for photorealistic novel view synthesis. We first optimize a hybrid neural volume-surface scene representation designed to have well-behaved level sets that correspond to surfaces in the scene. We then bake this representation into a high-quality triangle mesh, which we equip with a simple and fast view-dependent appearance model based on spherical Gaussians. Finally, we optimize this baked representation to best reproduce the captured viewpoints, resulting in a model that can leverage accelerated polygon rasterization pipelines for real-time view synthesis on commodity hardware. Our approach outperforms previous scene representations for real-time rendering in terms of accuracy, speed, and power consumption, and produces high quality meshes that enable applications such as appearance editing and physical simulation.


    1. Bao and 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 European Conference on Computer Vision (ECCV).
    2. Jonathan T. Barron. 2019. A General and Adaptive Robust Loss Function. CVPR (2019).
    3. Jonathan T. Barron, Ben Mildenhall, Dor Verbin, Pratul P. Srinivasan, and Peter Hedman. 2022. Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields. CVPR (2022).
    4. Yoshua Bengio, Nicholas Léonard, and Aaron Courville. 2013. Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:1308.3432 (2013).
    5. Alexander W. Bergman, Petr Kellnhofer, and Gordon Wetzstein. 2021. Fast Training of Neural Lumigraph Representations using Meta Learning. In NeurIPS.
    6. Mark Boss, Raphael Braun, Varun Jampani, Jonathan T. Barron, Ce Liu, and Hendrik P. A. Lensch. 2021. NeRD: Neural Reflectance Decomposition from Image Collections. ICCV (2021).
    7. 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. NeurIPS (2022).
    8. Chris Buehler, Michael Bosse, Leonard McMillan, Steven Gortler, and Michael Cohen. 2001. Unstructured Lumigraph Rendering. SIGGRAPH (2001).
    9. Anpei Chen, Zexiang Xu, Andreas Geiger, Jingyi Yu, and Hao Su. 2022b. TensoRF: Tensorial Radiance Fields. ECCV (2022).
    10. Zhiqin Chen, Thomas Funkhouser, Peter Hedman, and Andrea Tagliasacchi. 2022a. MobileNeRF: Exploiting the polygon rasterization pipeline for efficient neural field rendering on mobile architectures. arXiv:2208.00277 (2022).
    11. Paul E. Debevec, Camillo J. Taylor, and Jitendra Malik. 1996. Modeling and Rendering Architecture from Photographs: A hybrid geometry- and image-based approach. SIGGRAPH (1996).
    12. Yasutaka Furukawa and Carlos Hernández. 2015. Multi-View Stereo: A Tutorial. Foundations and Trends in Computer Graphics and Vision (2015).
    13. Stephan J. Garbin, Marek Kowalski, Matthew Johnson, Jamie Shotton, and Julien Valentin. 2021. FastNeRF: High-Fidelity Neural Rendering at 200FPS. ICCV (2021).
    14. Steven J. Gortler, Radek Grzeszczuk, Richard Szeliski, and Michael F. Cohen. 1996. The lumigraph. SIGGRAPH (1996).
    15. Amos Gropp, Lior Yariv, Niv Haim, Matan Atzmon, and Yaron Lipman. 2020. Implicit Geometric Regularization for Learning Shapes. Proceedings of Machine Learning and Systems (2020).
    16. Peter Hedman, Julien Philip, True Price, Jan-Michael Frahm, George Drettakis, and Gabriel Brostow. 2018. Deep blending for free-viewpoint image-based rendering. SIGGRAPH Asia (2018).
    17. Peter Hedman, Pratul P. Srinivasan, Ben Mildenhall, Jonathan T. Barron, and Paul Debevec. 2021. Baking Neural Radiance Fields for Real-Time View Synthesis. ICCV (2021).
    18. ISO/IEC 12113:2022 2022. Information technology — Runtime 3D asset delivery format — Khronos glTF 2.0. Standard. International Organization for Standardization.
    19. Michal Jancosek and Tomás Pajdla. 2011. Multi-view reconstruction preserving weakly-supported surfaces. (2011).
    20. Animesh Karnewar, Tobias Ritschel, Oliver Wang, and Niloy Mitra. 2022. ReLU fields: The little non-linearity that could. SIGGRAPH (2022).
    21. Michael Kazhdan, Matthew Bolitho, and Hugues Hoppe. 2006. Poisson Surface Reconstruction. Symposium on Geometry Processing (2006).
    22. Michael Kazhdan and Hugues Hoppe. 2013. Screened Poisson Surface Reconstruction. ACM TOG (2013).
    23. Georgios Kopanas, Julien Philip, Thomas Leimkühler, and George Drettakis. 2021. Point-Based Neural Rendering with Per-View Optimization. Computer Graphics Forum (2021).
    24. Zhengfei Kuang, Kyle Olszewski, Menglei Chai, Zeng Huang, Panos Achlioptas, and Sergey Tulyakov. 2022. NeROIC: Neural Rendering of Objects from Online Image Collections. SIGGRAPH (2022).
    25. Patrick Labatut, Jean-Philippe Pons, and Renaud Keriven. 2007. Efficient multi-view reconstruction of large-scale scenes using interest points, Delaunay triangulation and graph cuts. ICCV (2007).
    26. Marc Levoy and Pat Hanrahan. 1996. Light field rendering. SIGGRAPH (1996).
    27. Stephen Lombardi, Tomas Simon, Jason Saragih, Gabriel Schwartz, Andreas Lehrmann, and Yaser Sheikh. 2019. Neural Volumes: Learning Dynamic Renderable Volumes from Images. SIGGRAPH (2019).
    28. W. E. Lorensen and H. E. Cline. 1987. Marching cubes: A high resolution 3D surface construction algorithm. SIGGRAPH (1987).
    29. Nelson Max. 1995. Optical models for direct volume rendering. IEEE TVCG (1995).
    30. 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).
    31. Thomas Müller, Alex Evans, Christoph Schied, and Alexander Keller. 2022. Instant neural graphics primitives with a multiresolution hash encoding. SIGGRAPH (2022).
    32. Thomas Neff, Pascal Stadlbauer, Mathias Parger, Andreas Kurz, Joerg H. Mueller, Chakravarty R. Alla Chaitanya, Anton Kaplanyan, and Markus Steinberger. 2021. DONeRF: Towards Real-Time Rendering of Compact Neural Radiance Fields using Depth Oracle Networks. Computer Graphics Forum (2021).
    33. Michael Oechsle, Songyou Peng, and Andreas Geiger. 2021. UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction. ICCV (2021).
    34. Eric Penner and Li Zhang. 2017. Soft 3D Reconstruction for View Synthesis. SIGGRAPH Asia (2017).
    35. Christian Reiser, Songyou Peng, Yiyi Liao, and Andreas Geiger. 2021. KiloNeRF: Speeding up neural radiance fields with thousands of tiny MLPs. ICCV (2021).
    36. Christian Reiser, Richard Szeliski, Dor Verbin, Pratul P. Srinivasan, Ben Mildenhall, Andreas Geiger, Jonathan T. Barron, and Peter Hedman. 2023. MERF: Memory-Efficient Radiance Fields for Real-time View Synthesis in Unbounded Scenes. SIGGRAPH (2023).
    37. Gernot Riegler and Vladlen Koltun. 2020. Free View Synthesis. ECCV (2020).
    38. Gernot Riegler and Vladlen Koltun. 2021. Stable view synthesis. CVPR (2021).
    39. Darius Rückert, Linus Franke, and Marc Stamminger. 2022. ADOP: Approximate differentiable one-pixel point rendering. SIGGRAPH (2022).
    40. Pedro V. Sander, Diego Nehab, and Joshua Barczak. 2007. Fast Triangle Reordering for Vertex Locality and Reduced Overdraw. SIGGRAPH (2007).
    41. Johannes Lutz Schönberger, Enliang Zheng, Marc Pollefeys, and Jan-Michael Frahm. 2016. Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV (2016).
    42. 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. CVPR (2021).
    43. Pratul P. Srinivasan, Richard Tucker Joand nathan T. Barron, Ravi Ramamoorthi, Ren Ng, and Noah Snavely. 2019. Pushing the Boundaries of View Extrapolation with Multiplane Images. CVPR (2019).
    44. Cheng Sun, Min Sun, and Hwann-Tzong Chen. 2022. Direct voxel grid optimization: Super-fast convergence for radiance fields reconstruction. CVPR (2022).
    45. Richard Szeliski and Polina Golland. 1999. Stereo Matching with Transparency and Matting. IJCV (1999).
    46. 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. Computer Graphics Forum (2022).
    47. 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. CVPR (2022).
    48. G. Vogiatzis, C. Hernández, P. Torr, and R. Cipolla. 2007. Multi-View Stereo via Volumetric Graph-Cuts and Occlusion Robust Photo-Consistency. IEEE TPAMI (2007).
    49. 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).
    50. Suttisak Wizadwongsa, Pakkapon Phongthawee, Jiraphon Yenphraphai, and Supasorn Suwajanakorn. 2021. NeX: Real-time View Synthesis with Neural Basis Expansion. CVPR (2021).
    51. Daniel N. Wood, Daniel I. Azuma, Ken Aldinger, Brian Curless, Tom Duchamp, David H. Salesin, and Werner Stuetzle. 2000. Surface Light Fields for 3D Photography. SIGGRAPH (2000).
    52. Xiuchao Wu, Jiamin Xu, Zihan Zhu, Hujun Bao, Qixing Huang, James Tompkin, and Weiwei Xu. 2022. Scalable Neural Indoor Scene Rendering. ACM TOG (2022).
    53. Lior Yariv, Jiatao Gu, Yoni Kasten, and Yaron Lipman. 2021. Volume rendering of neural implicit surfaces. NeurIPS (2021).
    54. Alex Yu, Sara Fridovich-Keil, Matthew Tancik, Qinhong Chen, Benjamin Recht, and Angjoo Kanazawa. 2022. Plenoxels: Radiance fields without neural networks. CVPR (2022).
    55. Alex Yu, Ruilong Li, Matthew Tancik, Hao Li, Ren Ng, and Angjoo Kanazawa. 2021. PlenOctrees for real-time rendering of neural radiance fields. ICCV (2021).
    56. 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. CVPR (2021).
    57. Kai Zhang, Gernot Riegler, Noah Snavely, and Vladlen Koltun. 2020. NeRF++: Analyzing and Improving Neural Radiance Fields. arXiv:2010.07492 (2020).
    58. 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. SIGGRAPH Asia (2021).
    59. Tinghui Zhou, Richard Tucker, John Flynn, Graham Fyffe, and Noah Snavely. 2018. Stereo Magnification: Learning View Synthesis Using Multiplane Images. SIGGRAPH (2018).

Additional Images:

©Lior Yariv, Peter Hedman, Christian Reiser, Dor Verbin, Pratul P. Srinivasan, Richard Szeliski, Jonathan T. Barron, and Ben Mildenhall

ACM Digital Library Publication:

Overview Page: