“Nerfstudio: A Modular Framework for Neural Radiance Field Development” by Tancik, Weber, Ng, Li, Yi, et al. …

  • ©Matthew Tancik, Ethan Weber, Evonne Ng, Ruilong Li, Brent Yi, Alexander Kristoffersen, Jake Austin, Kamyar Salahi, Abhik Ahuja, David F. McAllister, Justin Kerr, and Angjoo Kanazawa




    Nerfstudio: A Modular Framework for Neural Radiance Field Development

Session/Category Title: Environmental Rendering: NeRFs On Earth




    Neural Radiance Fields (NeRF) are a rapidly growing area of research with wide-ranging applications in computer vision, graphics, robotics, and more. In order to streamline the development and deployment of NeRF research, we propose a modular PyTorch framework, Nerfstudio. Our framework includes plug-and-play components for implementing NeRF-based methods, which make it easy for researchers and practitioners to incorporate NeRF into their projects. Additionally, the modular design enables support for extensive real-time visualization tools, streamlined pipelines for importing captured in-the-wild data, and tools for exporting to video, point cloud and mesh representations. The modularity of Nerfstudio enables the development of Nerfacto, our method that combines components from recent papers to achieve a balance between speed and quality, while also remaining flexible to future modifications. To promote community-driven development, all associated code and data are made publicly available with open-source licensing.


    1. Martín Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, 2016. { TensorFlow} : a system for { Large-Scale} machine learning. In 12th USENIX symposium on operating systems design and implementation (OSDI 16). 265–283.
    2. Michal Adamkiewicz, Timothy Chen, Adam Caccavale, Rachel Gardner, Preston Culbertson, Jeannette Bohg, and Mac Schwager. 2021. Vision-Only Robot Navigation in a Neural Radiance World. CoRR abs/2110.00168 (2021). arXiv:2110.00168https://arxiv.org/abs/2110.00168
    3. Jonathan T Barron, Ben Mildenhall, Matthew Tancik, Peter Hedman, Ricardo Martin-Brualla, and Pratul P Srinivasan. 2021. Mip-nerf: A multiscale representation for anti-aliasing neural radiance fields. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 5855–5864.
    4. Jonathan T Barron, Ben Mildenhall, Dor Verbin, Pratul P Srinivasan, and Peter Hedman. 2022. Mip-nerf 360: Unbounded anti-aliased neural radiance fields. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 5470–5479.
    5. Arunkumar Byravan, Jan Humplik, Leonard Hasenclever, Arthur Brussee, Francesco Nori, Tuomas Haarnoja, Ben Moran, Steven Bohez, Fereshteh Sadeghi, Bojan Vujatovic, and Nicolas Heess. 2022. NeRF2Real: Sim2real Transfer of Vision-guided Bipedal Motion Skills using Neural Radiance Fields. https://doi.org/10.48550/ARXIV.2210.04932
    6. Anpei Chen, Zexiang Xu, Andreas Geiger, Jingyi Yu, and Hao Su. 2022. TensoRF: Tensorial Radiance Fields. In European Conference on Computer Vision (ECCV).
    7. Robert L Cook, Loren Carpenter, and Edwin Catmull. 1987. The Reyes image rendering architecture. ACM SIGGRAPH Computer Graphics 21, 4 (1987), 95–102.
    8. Danny Driess, Zhiao Huang, Yunzhu Li, Russ Tedrake, and Marc Toussaint. 2022. Learning Multi-Object Dynamics with Compositional Neural Radiance Fields. arXiv preprint arXiv:2202.11855 (2022).
    9. Sara Fridovich-Keil, Alex Yu, Matthew Tancik, Qinhong Chen, Benjamin Recht, and Angjoo Kanazawa. 2022. Plenoxels: Radiance Fields Without Neural Networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 5501–5510.
    10. S. J. Garbin, M. Kowalski, M. Johnson, J. Shotton, and J. Valentin. 2021. FastNeRF: High-Fidelity Neural Rendering at 200FPS. In 2021 IEEE/CVF International Conference on Computer Vision (ICCV). IEEE Computer Society, Los Alamitos, CA, USA, 14326–14335. https://doi.org/10.1109/ICCV48922.2021.01408
    11. 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).
    12. Yuanming Hu, Tzu-Mao Li, Luke Anderson, Jonathan Ragan-Kelley, and Frédo Durand. 2019. Taichi: a language for high-performance computation on spatially sparse data structures. ACM Transactions on Graphics (TOG) 38, 6 (2019), 1–16.
    13. Wenzel Jakob, Sébastien Speierer, Nicolas Roussel, Merlin Nimier-David, Delio Vicini, Tizian Zeltner, Baptiste Nicolet, Miguel Crespo, Vincent Leroy, and Ziyi Zhang. 2022. Mitsuba 3 renderer. https://mitsuba-renderer.org.
    14. Yoonwoo Jeong, Seungjoo Shin, and Kibaek Park. 2022. NeRF-Factory: An awesome PyTorch NeRF collection. https://github.com/kakaobrain/NeRF-Factory/
    15. Yangqing Jia, Evan Shelhamer, Jeff Donahue, Sergey Karayev, Jonathan Long, Ross Girshick, Sergio Guadarrama, and Trevor Darrell. 2014. Caffe: Convolutional architecture for fast feature embedding. In Proceedings of the 22nd ACM international conference on Multimedia. 675–678.
    16. Michael Kazhdan, Matthew Bolitho, and Hugues Hoppe. 2006. Poisson surface reconstruction. In Proceedings of the fourth Eurographics symposium on Geometry processing, Vol. 7.
    17. Justin Kerr, Letian Fu, Huang Huang, Yahav Avigal, Matthew Tancik, Jeffrey Ichnowski, Angjoo Kanazawa, and Ken Goldberg. 2022. Evo-NeRF: Evolving NeRF for Sequential Robot Grasping of Transparent Objects. In 6th Annual Conference on Robot Learning.
    18. Ruilong Li, Matthew Tancik, and Angjoo Kanazawa. 2022. NerfAcc: A General NeRF Accleration Toolbox.arXiv preprint arXiv:2210.04847 (2022).
    19. Chen-Hsuan Lin, Wei-Chiu Ma, Antonio Torralba, and Simon Lucey. 2021. Barf: Bundle-adjusting neural radiance fields. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 5741–5751.
    20. Lingjie Liu, Jiatao Gu, Kyaw Zaw Lin, Tat-Seng Chua, and Christian Theobalt. 2020. Neural sparse voxel fields. Advances in Neural Information Processing Systems 33 (2020), 15651–15663.
    21. Ricardo Martin-Brualla, Noha Radwan, Mehdi SM Sajjadi, Jonathan T Barron, Alexey Dosovitskiy, and Daniel Duckworth. 2021. Nerf in the wild: Neural radiance fields for unconstrained photo collections. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 7210–7219.
    22. Ben Mildenhall, Peter Hedman, Ricardo Martin-Brualla, Pratul P Srinivasan, and Jonathan T Barron. 2022a. Nerf in the dark: High dynamic range view synthesis from noisy raw images. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 16190–16199.
    23. Ben Mildenhall, Pratul P Srinivasan, Rodrigo Ortiz-Cayon, Nima Khademi Kalantari, Ravi Ramamoorthi, Ren Ng, and Abhishek Kar. 2019. Local light field fusion: Practical view synthesis with prescriptive sampling guidelines. ACM Transactions on Graphics (TOG) 38, 4 (2019), 1–14.
    24. Ben Mildenhall, Pratul P Srinivasan, Matthew Tancik, Jonathan T Barron, Ravi Ramamoorthi, and Ren Ng. 2021. Nerf: Representing scenes as neural radiance fields for view synthesis. Commun. ACM 65, 1 (2021), 99–106.
    25. Ben Mildenhall, Dor Verbin, Pratul P. Srinivasan, Peter Hedman, Ricardo Martin-Brualla, and Jonathan T. Barron. 2022b. MultiNeRF: A Code Release for Mip-NeRF 360, Ref-NeRF, and RawNeRF. https://github.com/google-research/multinerf
    26. Thomas Müller. 2021. tiny-cuda-nn. https://github.com/NVlabs/tiny-cuda-nn
    27. Thomas Müller, Alex Evans, Christoph Schied, and Alexander Keller. 2022. Instant neural graphics primitives with a multiresolution hash encoding. arXiv preprint arXiv:2201.05989 (2022).
    28. Krishna Murthy. 2020. nerf-pytorch: A PyTorch re-implementation. https://github.com/krrish94/nerf-pytorch
    29. Thomas Neff, Pascal Stadlbauer, Mathias Parger, Andreas Kurz, Joerg H. Mueller, Chakravarty R. Alla Chaitanya, Anton S. Kaplanyan, and Markus Steinberger. 2021. DONeRF: Towards Real-Time Rendering of Compact Neural Radiance Fields using Depth Oracle Networks. Computer Graphics Forum 40, 4 (2021). https://doi.org/10.1111/cgf.14340
    30. Michael Oechsle, Songyou Peng, and Andreas Geiger. 2021. Unisurf: Unifying neural implicit surfaces and radiance fields for multi-view reconstruction. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 5589–5599.
    31. Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32 (2019).
    32. Georgios Pavlakos, Ethan Weber, Matthew Tancik, and Angjoo Kanazawa. 2022. The One Where They Reconstructed 3D Humans and Environments in TV Shows. In European Conference on Computer Vision. Springer, 732–749.
    33. Ben Poole, Ajay Jain, Jonathan T. Barron, and Ben Mildenhall. 2023. DreamFusion: Text-to-3D using 2D Diffusion. In The Eleventh International Conference on Learning Representations. https://openreview.net/forum?id=FjNys5c7VyY
    34. Albert Pumarola, Enric Corona, Gerard Pons-Moll, and Francesc Moreno-Noguer. 2021. D-nerf: Neural radiance fields for dynamic scenes. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 10318–10327.
    35. Chen Quei-An. 2020. Nerf_pl: a pytorchlightning implementation of NeRF. https://github.com/kwea123/nerf_pl/
    36. Jonathan Ragan-Kelley, Connelly Barnes, Andrew Adams, Sylvain Paris, Frédo Durand, and Saman Amarasinghe. 2013. Halide: a language and compiler for optimizing parallelism, locality, and recomputation in image processing pipelines. Acm Sigplan Notices 48, 6 (2013), 519–530.
    37. Nikhila Ravi, Jeremy Reizenstein, David Novotny, Taylor Gordon, Wan-Yen Lo, Justin Johnson, and Georgia Gkioxari. 2020. Accelerating 3d deep learning with pytorch3d. arXiv preprint arXiv:2007.08501 (2020).
    38. Christian Reiser, Songyou Peng, Yiyi Liao, and Andreas Geiger. 2021. KiloNeRF: Speeding Up Neural Radiance Fields With Thousands of Tiny MLPs. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). 14335–14345.
    39. Edgar Riba, Dmytro Mishkin, Daniel Ponsa, Ethan Rublee, and Gary Bradski. 2020. Kornia: an open source differentiable computer vision library for pytorch. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. 3674–3683.
    40. Darius Rückert, Yuanhao Wang, Rui Li, Ramzi Idoughi, and Wolfgang Heidrich. 2022. NeAT: Neural Adaptive Tomography. ACM Trans. Graph. 41, 4, Article 55 (jul 2022), 13 pages. https://doi.org/10.1145/3528223.3530121
    41. Johannes Lutz Schönberger and Jan-Michael Frahm. 2016. Structure-from-Motion Revisited. In Conference on Computer Vision and Pattern Recognition (CVPR).
    42. Johannes Lutz Schönberger, True Price, Torsten Sattler, Jan-Michael Frahm, and Marc Pollefeys. 2016a. A Vote-and-Verify Strategy for Fast Spatial Verification in Image Retrieval. In Asian Conference on Computer Vision (ACCV).
    43. Johannes Lutz Schönberger, Enliang Zheng, Marc Pollefeys, and Jan-Michael Frahm. 2016b. Pixelwise View Selection for Unstructured Multi-View Stereo. In European Conference on Computer Vision (ECCV).
    44. Anthony Simeonov, Yilun Du, Andrea Tagliasacchi, Joshua B. Tenenbaum, Alberto Rodriguez, Pulkit Agrawal, and Vincent Sitzmann. 2022. Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulation. In ICRA. 6394–6400. https://doi.org/10.1109/ICRA46639.2022.9812146
    45. Noah Snavely, Steven M Seitz, and Richard Szeliski. 2006. Photo tourism: exploring photo collections in 3D. In ACM siggraph 2006 papers. 835–846.
    46. Cheng Sun, Min Sun, and Hwann-Tzong Chen. 2022. Direct voxel grid optimization: Super-fast convergence for radiance fields reconstruction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 5459–5469.
    47. Towaki Takikawa, Or Perel, Clement Fuji Tsang, Charles Loop, Joey Litalien, Jonathan Tremblay, Sanja Fidler, and Maria Shugrina. 2022. Kaolin Wisp: A PyTorch Library and Engine for Neural Fields Research. https://github.com/NVIDIAGameWorks/kaolin-wisp.
    48. Matthew Tancik, Vincent Casser, Xinchen Yan, Sabeek Pradhan, Ben Mildenhall, Pratul Srinivasan, Jonathan T. Barron, and Henrik Kretzschmar. 2022. Block-NeRF: Scalable Large Scene Neural View Synthesis. arXiv (2022).
    49. 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 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 5481–5490.
    50. Can Wang, Menglei Chai, Mingming He, Dongdong Chen, and Jing Liao. 2022. Clip-nerf: Text-and-image driven manipulation of neural radiance fields. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 3835–3844.
    51. Peng Wang, Lingjie Liu, Yuan Liu, Christian Theobalt, Taku Komura, and Wenping Wang. 2021a. Neus: Learning neural implicit surfaces by volume rendering for multi-view reconstruction. arXiv preprint arXiv:2106.10689 (2021).
    52. Qianqian Wang, Zhicheng Wang, Kyle Genova, Pratul P Srinivasan, Howard Zhou, Jonathan T Barron, Ricardo Martin-Brualla, Noah Snavely, and Thomas Funkhouser. 2021b. Ibrnet: Learning multi-view image-based rendering. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 4690–4699.
    53. Zirui Wang, Shangzhe Wu, Weidi Xie, Min Chen, and Victor Adrian Prisacariu. 2021c. NeRF–: Neural radiance fields without known camera parameters. arXiv preprint arXiv:2102.07064 (2021).
    54. Katherine Watson, Alexandre Devaux, Niko Koppel, A.J. Chavar, and Peter Whidden. 2022. Creating workflows for NeRF Portraiture. https://rd.nytimes.com/projects/creating-workflows-for-nerf-portraiture
    55. Yiheng Xie, Towaki Takikawa, Shunsuke Saito, Or Litany, Shiqin Yan, Numair Khan, Federico Tombari, James Tompkin, Vincent Sitzmann, and Srinath Sridhar. 2022. Neural fields in visual computing and beyond. In Computer Graphics Forum, Vol. 41. Wiley Online Library, 641–676.
    56. Lior Yariv, Jiatao Gu, Yoni Kasten, and Yaron Lipman. 2021. Volume rendering of neural implicit surfaces. Advances in Neural Information Processing Systems 34 (2021), 4805–4815.
    57. Lin Yen-Chen. 2020. NeRF-pytorch. https://github.com/yenchenlin/nerf-pytorch/.
    58. Alex Yu, Vickie Ye, Matthew Tancik, and Angjoo Kanazawa. 2021. pixelnerf: Neural radiance fields from one or few images. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 4578–4587.
    59. Zehao Yu, Anpei Chen, Bozidar Antic, Songyou Peng, Apratim Bhattacharyya, Michael Niemeyer, Siyu Tanga, Torsten Sattler, and Andreas Geiger. 2022. SDFStudio: A Unified Framework for Surface Reconstruction. https://github.com/autonomousvision/sdfstudio
    60. Yan-Pei Cao Yue Luo. 2022. ArcNerf: Nerf-based object/scene rendering and extraction framework. https://github.com/TencentARC/arcnerf/
    61. Kai Zhang, Nick Kolkin, Sai Bi, Fujun Luan, Zexiang Xu, Eli Shechtman, and Noah Snavely. 2022. Arf: Artistic radiance fields. In Computer Vision–ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part XXXI. Springer, 717–733.
    62. Jun-Yan Zhu, Yong Jae Lee, and Alexei A Efros. 2014. Averageexplorer: Interactive exploration and alignment of visual data collections. ACM Transactions on Graphics (TOG) 33, 4 (2014), 1–11.
    63. Zihan Zhu, Songyou Peng, Viktor Larsson, Weiwei Xu, Hujun Bao, Zhaopeng Cui, Martin R. Oswald, and Marc Pollefeys. 2022. NICE-SLAM: Neural Implicit Scalable Encoding for SLAM. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

ACM Digital Library Publication:

Overview Page: