“ViP-NeRF: Visibility Prior for Sparse Input Neural Radiance Fields” by Somraj and Soundararajan
Conference:
Type(s):
Title:
- ViP-NeRF: Visibility Prior for Sparse Input Neural Radiance Fields
Session/Category Title: Environmental Rendering: NeRFs on Earth
Presenter(s)/Author(s):
Moderator(s):
Abstract:
Neural radiance fields (NeRF) have achieved impressive performances in view synthesis by encoding neural representations of a scene. However, NeRFs require hundreds of images per scene to synthesize photo-realistic novel views. Training them on sparse input views leads to overfitting and incorrect scene depth estimation resulting in artifacts in the rendered novel views. Sparse input NeRFs were recently regularized by providing dense depth estimated from pre-trained networks as supervision, to achieve improved performance over sparse depth constraints. However, we find that such depth priors may be inaccurate due to generalization issues. Instead, we hypothesize that the visibility of pixels in different input views can be more reliably estimated to provide dense supervision. In this regard, we compute a visibility prior through the use of plane sweep volumes, which does not require any pre-training. By regularizing the NeRF training with the visibility prior, we successfully train the NeRF with few input views. We reformulate the NeRF to also directly output the visibility of a 3D point from a given viewpoint to reduce the training time with the visibility constraint. On multiple datasets, our model outperforms the competing sparse input NeRF models including those that use learned priors. The source code for our model can be found on our project page: https://nagabhushansn95.github.io/publications/2023/ViP-NeRF.html.
References:
1. 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 (ICCV).
2. 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 (CVPR).
3. Shengqu Cai, Anton Obukhov, Dengxin Dai, and Luc Van Gool. 2022. Pix2NeRF: Unsupervised Conditional p-GAN for Single Image to Neural Radiance Fields Translation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
4. Eric R. Chan, Marco Monteiro, Petr Kellnhofer, Jiajun Wu, and Gordon Wetzstein. 2021. Pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
5. Anpei Chen, Zexiang Xu, Fuqiang Zhao, Xiaoshuai Zhang, Fanbo Xiang, Jingyi Yu, and Hao Su. [n. d.]. MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo. arXiv e-prints, Article arXiv:2103.15595 ([n. d.]).
6. R.T. Collins. 1996. A Space-Sweep Approach to True Multi-Image Matching. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/CVPR.1996.517097
7. Gregory W Corder and Dale I Foreman. 2014. Nonparametric statistics: A step-by-step approach.
8. Kangle Deng, Andrew Liu, Jun-Yan Zhu, and Deva Ramanan. 2022. Depth-Supervised NeRF: Fewer Views and Faster Training for Free. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
9. David Gallup, Jan-Michael Frahm, Philippos Mordohai, Qingxiong Yang, and Marc Pollefeys. 2007. Real-Time Plane-Sweeping Stereo with Multiple Sweeping Directions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/CVPR.2007.383245
10. Chen Gao, Yichang Shih, Wei-Sheng Lai, Chia-Kai Liang, and Jia-Bin Huang. [n. d.]. Portrait Neural Radiance Fields from a Single Image. arXiv e-prints, Article arXiv:2012.05903 ([n. d.]).
11. Hyowon Ha, Sunghoon Im, Jaesik Park, Hae-Gon Jeon, and In So Kweon. 2016. High-Quality Depth From Uncalibrated Small Motion Clip. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
12. Abdullah Hamdi, Bernard Ghanem, and Matthias Nießner. [n. d.]. SPARF: Large-Scale Learning of 3D Sparse Radiance Fields from Few Input Images. arXiv e-prints, Article arXiv:2212.09100 ([n. d.]).
13. Yuxuan Han, Ruicheng Wang, and Jiaolong Yang. 2022. Single-View View Synthesis in the Wild with Learned Adaptive Multiplane Images. In Proceedings of the ACM SIGGRAPH.
14. Po-Han Huang, Kevin Matzen, Johannes Kopf, Narendra Ahuja, and Jia-Bin Huang. 2018. DeepMVS: Learning Multi-View Stereopsis. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
15. Sunghoon Im, Hae-Gon Jeon, Stephen Lin, and In So Kweon. [n. d.]. DPSNet: End-to-end Deep Plane Sweep Stereo. arXiv e-prints, Article arXiv:1905.00538 ([n. d.]).
16. Ajay Jain, Matthew Tancik, and Pieter Abbeel. 2021. Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesis. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV).
17. Mohammad Mahdi Johari, Yann Lepoittevin, and François Fleuret. 2022. GeoNeRF: Generalizing NeRF With Geometry Priors. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
18. Mijeong Kim, Seonguk Seo, and Bohyung Han. 2022. InfoNeRF: Ray Entropy Minimization for Few-Shot Neural Volume Rendering. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
19. Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2012. ImageNet Classification with Deep Convolutional Neural Networks. In Proceedings of the Advances in Neural Information Processing Systems (NeurIPS).
20. Jiaxin Li, Zijian Feng, Qi She, Henghui Ding, Changhu Wang, and Gim Hee Lee. 2021. MINE: Towards Continuous Depth MPI With NeRF for Novel View Synthesis. In Proceedings of the IEEE International Conference on Computer Vision (ICCV).
21. Kai-En Lin, Yen-Chen Lin, Wei-Sheng Lai, Tsung-Yi Lin, Yi-Chang Shih, and Ravi Ramamoorthi. 2023. Vision Transformer for NeRF-Based View Synthesis From a Single Input Image. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV).
22. Yuan Liu, Sida Peng, Lingjie Liu, Qianqian Wang, Peng Wang, Christian Theobalt, Xiaowei Zhou, and Wenping Wang. 2022. Neural Rays for Occlusion-Aware Image-Based Rendering. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
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 (July 2019), 1–14. https://doi.org/10.1145/3306346.3322980
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 Proceedings of the European Conference on Computer Vision (ECCV).
25. Michael Niemeyer, Jonathan T. Barron, Ben Mildenhall, Mehdi S. M. Sajjadi, Andreas Geiger, and Noha Radwan. 2022. RegNeRF: Regularizing Neural Radiance Fields for View Synthesis From Sparse Inputs. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
26. Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proceedings of the International Conference on Machine Learning (ICML).
27. Barbara Roessle, Jonathan T. Barron, Ben Mildenhall, Pratul P. Srinivasan, and Matthias Nießner. 2022. Dense Depth Priors for Neural Radiance Fields From Sparse Input Views. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
28. Pratul P. Srinivasan, Richard Tucker, Jonathan T. Barron, Ravi Ramamoorthi, Ren Ng, and Noah Snavely. 2019. Pushing the Boundaries of View Extrapolation With Multiplane Images. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
29. Matthew Tancik, Ben Mildenhall, Terrance Wang, Divi Schmidt, Pratul P. Srinivasan, Jonathan T. Barron, and Ren Ng. 2021. Learned Initializations for Optimizing Coordinate-Based Neural Representations. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
30. Richard Tucker and Noah Snavely. 2020. Single-View View Synthesis With Multiplane Images. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
31. Qianqian Wang, Zhicheng Wang, Kyle Genova, Pratul P. Srinivasan, Howard Zhou, Jonathan T. Barron, Ricardo Martin-Brualla, Noah Snavely, and Thomas Funkhouser. 2021. IBRNet: Learning Multi-View Image-Based Rendering. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
32. 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 (TIP) 13, 4 (2004), 600–612.
33. Olivia Wiles, Georgia Gkioxari, Richard Szeliski, and Justin Johnson. 2020. SynSin: End-to-End View Synthesis From a Single Image. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
34. Felix Wimbauer, Nan Yang, Christian Rupprecht, and Daniel Cremers. [n. d.]. Behind the Scenes: Density Fields for Single View Reconstruction. arXiv e-prints, Article arXiv:2301.07668 ([n. d.]).
35. Jamie Wynn and Daniyar Turmukhambetov. [n. d.]. DiffusioNeRF: Regularizing Neural Radiance Fields with Denoising Diffusion Models. arXiv e-prints, Article arXiv:2302.12231 ([n. d.]).
36. Dejia Xu, Yifan Jiang, Peihao Wang, Zhiwen Fan, Humphrey Shi, and Zhangyang Wang. 2022. SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image. In Proceedings of the European Conference on Computer Vision (ECCV).
37. Ruigang Yang and M. Pollefeys. 2003. Multi-Resolution Real-Time Stereo on Commodity Graphics Hardware. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/CVPR.2003.1211356
38. Zhenpei Yang, Zhile Ren, Miguel Angel Bautista, Zaiwei Zhang, Qi Shan, and Qixing Huang. 2022. FvOR: Robust Joint Shape and Pose Optimization for Few-View Object Reconstruction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
39. Alex Yu, Vickie Ye, Matthew Tancik, and Angjoo Kanazawa. 2021. pixelNeRF: Neural Radiance Fields From One or Few Images. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
40. Jason Zhang, Gengshan Yang, Shubham Tulsiani, and Deva Ramanan. 2021. NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wild. In Proceedings of the Advances in Neural Information Processing Systems (NeurIPS).
41. Richard Zhang, Phillip Isola, Alexei A Efros, Eli Shechtman, and Oliver Wang. 2018. The Unreasonable Effectiveness of Deep Features as a Perceptual Metric. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
42. Tinghui Zhou, Richard Tucker, John Flynn, Graham Fyffe, and Noah Snavely. 2018. Stereo Magnification: Learning View Synthesis Using Multiplane Images. ACM Transactions on Graphics (TOG) 37, 4 (July 2018).
43. Zhizhuo Zhou and Shubham Tulsiani. [n. d.]. SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstruction. arXiv e-prints, Article arXiv:2212.00792 ([n. d.]).
Additional Images:
![©Nagabhushan Somraj and Rajiv Soundararajan](https://history.siggraph.org/wp-content/uploads/2024/02/2023-Tech-Papers-Somraj_ViP-NeRF-Visibility-Prior-for-Sparse-Input-Neural-Radiance-Fields-02.jpg)