ABSTRACT
We propose to tackle the multiview photometric stereo problem using an extension of Neural Radiance Fields (NeRFs), conditioned on light source direction. The geometric part of our neural representation predicts surface normal direction, allowing us to reason about local surface reflectance. The appearance part of our neural representation is decomposed into a neural bidirectional reflectance function (BRDF), learnt as part of the fitting process, and a shadow prediction network (conditioned on light source direction) allowing us to model the apparent BRDF. This balance of learnt components with inductive biases based on physical image formation models allows us to extrapolate far from the light source and viewer directions observed during training. We demonstrate our approach on a multiview photometric stereo benchmark and show that competitive performance can be obtained with the neural density representation of a NeRF.
- Piotr Bojanowski, Armand Joulin, David Lopez-Paz, and Arthur Szlam. 2017. Optimizing the latent space of generative networks. arXiv preprint arXiv:1707.05776(2017).Google Scholar
- Mark Boss, Raphael Braun, Varun Jampani, Jonathan T Barron, Ce Liu, and Hendrik Lensch. 2021. Nerd: Neural reflectance decomposition from image collections. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 12684–12694.Google ScholarCross Ref
- Wenzheng Chen, Huan Ling, Jun Gao, Edward Smith, Jaakko Lehtinen, Alec Jacobson, and Sanja Fidler. 2019. Learning to predict 3d objects with an interpolation-based differentiable renderer. Advances in Neural Information Processing Systems 32 (2019).Google Scholar
- John Flynn, Michael Broxton, Paul Debevec, Matthew DuVall, Graham Fyffe, Ryan Overbeck, Noah Snavely, and Richard Tucker. 2019. Deepview: View synthesis with learned gradient descent. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2367–2376.Google ScholarCross Ref
- Matheus Gadelha, Subhransu Maji, and Rui Wang. 2017. 3d shape induction from 2d views of multiple objects. In 2017 International Conference on 3D Vision (3DV). IEEE, 402–411.Google ScholarCross Ref
- Kyle Genova, Forrester Cole, Avneesh Sud, Aaron Sarna, and Thomas Funkhouser. 2020. Local deep implicit functions for 3d shape. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 4857–4866.Google ScholarCross Ref
- Philipp Henzler, Niloy J Mitra, and Tobias Ritschel. 2020. Learning a neural 3d texture space from 2d exemplars. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 8356–8364.Google ScholarCross Ref
- Ruo Huang, Shelby McIntyre, Meina Song, Zhonghong Ou, 2020. An attention-based latent information extraction network (ALIEN) for high-order feature interactions. Applied Sciences 10, 16 (2020), 5468.Google ScholarCross Ref
- Chiyu Jiang, Avneesh Sud, Ameesh Makadia, Jingwei Huang, Matthias Nießner, Thomas Funkhouser, 2020. Local implicit grid representations for 3d scenes. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 6001–6010.Google ScholarCross Ref
- James T Kajiya and Brian P Von Herzen. 1984. Ray tracing volume densities. ACM SIGGRAPH computer graphics 18, 3 (1984), 165–174.Google Scholar
- Angjoo Kanazawa, Shubham Tulsiani, Alexei A Efros, and Jitendra Malik. 2018. Learning category-specific mesh reconstruction from image collections. In Proceedings of the European Conference on Computer Vision (ECCV). 371–386.Google ScholarDigital Library
- Marc Levoy. 1990. Efficient ray tracing of volume data. ACM Transactions on Graphics (TOG) 9, 3 (1990), 245–261.Google ScholarDigital Library
- Min Li, Zhenglong Zhou, Zhe Wu, Boxin Shi, Changyu Diao, and Ping Tan. 2020. Multi-view photometric stereo: A robust solution and benchmark dataset for spatially varying isotropic materials. IEEE Transactions on Image Processing 29 (2020), 4159–4173.Google ScholarDigital Library
- Tzu-Mao Li, Miika Aittala, Frédo Durand, and Jaakko Lehtinen. 2018. Differentiable monte carlo ray tracing through edge sampling. ACM Transactions on Graphics (TOG) 37, 6 (2018), 1–11.Google ScholarDigital Library
- Yiyi Liao, Simon Donne, and Andreas Geiger. 2018. Deep marching cubes: Learning explicit surface representations. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2916–2925.Google ScholarCross Ref
- D. B.* Lindell, J. N. P.* Martel, and G. Wetzstein. 2021. AutoInt: Automatic Integration for Fast Neural Volume Rendering. In Proc. CVPR.Google Scholar
- 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.Google Scholar
- Shichen Liu, Tianye Li, Weikai Chen, and Hao Li. 2019. Soft rasterizer: A differentiable renderer for image-based 3d reasoning. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 7708–7717.Google ScholarCross Ref
- Stephen Lombardi, Tomas Simon, Jason Saragih, Gabriel Schwartz, Andreas Lehrmann, and Yaser Sheikh. 2019. Neural volumes: Learning dynamic renderable volumes from images. arXiv preprint arXiv:1906.07751(2019).Google Scholar
- 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.Google ScholarCross Ref
- Nelson Max. 1995. Optical models for direct volume rendering. IEEE Transactions on Visualization and Computer Graphics 1, 2(1995), 99–108.Google ScholarDigital Library
- Lars Mescheder, Michael Oechsle, Michael Niemeyer, Sebastian Nowozin, and Andreas Geiger. 2019. Occupancy networks: Learning 3d reconstruction in function space. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 4460–4470.Google ScholarCross Ref
- Ben Mildenhall, Peter Hedman, Ricardo Martin-Brualla, Pratul P. Srinivasan, and Jonathan T. Barron. 2021. NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Images. arXiv (2021).Google Scholar
- 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.Google ScholarDigital Library
- 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.Google Scholar
- Michael Niemeyer, Lars Mescheder, Michael Oechsle, and Andreas Geiger. 2020. Differentiable volumetric rendering: Learning implicit 3d representations without 3d supervision. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 3504–3515.Google ScholarCross Ref
- Michael Oechsle, Lars Mescheder, Michael Niemeyer, Thilo Strauss, and Andreas Geiger. 2019. Texture fields: Learning texture representations in function space. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 4531–4540.Google ScholarCross Ref
- Junyi Pan, Xiaoguang Han, Weikai Chen, Jiapeng Tang, and Kui Jia. 2019. Deep mesh reconstruction from single rgb images via topology modification networks. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 9964–9973.Google ScholarCross Ref
- Jeong Joon Park, Peter Florence, Julian Straub, Richard Newcombe, and Steven Lovegrove. 2019. Deepsdf: Learning continuous signed distance functions for shape representation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 165–174.Google ScholarCross Ref
- Nasim Rahaman, Aristide Baratin, Devansh Arpit, Felix Draxler, Min Lin, Fred Hamprecht, Yoshua Bengio, and Aaron Courville. 2019. On the spectral bias of neural networks. In International Conference on Machine Learning. PMLR, 5301–5310.Google Scholar
- Daniel Rebain, Wei Jiang, Soroosh Yazdani, Ke Li, Kwang Moo Yi, and Andrea Tagliasacchi. 2021. Derf: Decomposed radiance fields. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 14153–14161.Google ScholarCross Ref
- Szymon M Rusinkiewicz. 1998. A new change of variables for efficient BRDF representation. In Eurographics Workshop on Rendering Techniques. Springer, 11–22.Google ScholarCross Ref
- Vincent Sitzmann, Michael Zollhöfer, and Gordon Wetzstein. 2019. Scene representation networks: Continuous 3d-structure-aware neural scene representations. Advances in Neural Information Processing Systems 32 (2019).Google Scholar
- 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 Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 7495–7504.Google ScholarCross Ref
- David Stutz and Andreas Geiger. 2018. Learning 3d shape completion from laser scan data with weak supervision. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1955–1964.Google ScholarCross Ref
- Nanyang Wang, Yinda Zhang, Zhuwen Li, Yanwei Fu, Wei Liu, and Yu-Gang Jiang. 2018. Pixel2mesh: Generating 3d mesh models from single rgb images. In Proceedings of the European conference on computer vision (ECCV). 52–67.Google ScholarDigital Library
- 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.Google Scholar
- Haozhe Xie, Hongxun Yao, Xiaoshuai Sun, Shangchen Zhou, and Shengping Zhang. 2019. Pix2vox: Context-aware 3d reconstruction from single and multi-view images. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 2690–2698.Google ScholarCross Ref
- Kai Zhang, Gernot Riegler, Noah Snavely, and Vladlen Koltun. 2020. Nerf++: Analyzing and improving neural radiance fields. arXiv preprint arXiv:2010.07492(2020).Google Scholar
- Xiuming Zhang, Pratul P Srinivasan, Boyang Deng, Paul Debevec, William T Freeman, and Jonathan T Barron. 2021. NeRFactor: Neural Factorization of Shape and Reflectance Under an Unknown Illumination. arXiv preprint arXiv:2106.01970(2021).Google Scholar
Recommendations
Efficient Photometric Stereo Technique for Three-Dimensional Surfaces with Unknown BRDF
3DIM '05: Proceedings of the Fifth International Conference on 3-D Digital Imaging and ModelingThe present paper focuses on efficient inverse rendering using a Photometric Stereo technique for realistic surfaces. The technique primarily assumes the Lambertian reflection model only. For non-Lambertian surfaces, application of the technique to real ...
Interreflection removal for photometric stereo by using spectrum-dependent albedo
CVPR '11: Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern RecognitionWe present a novel method that can separate m-bounced light and remove the interreflections in a photometric stereo setup. Under the assumption of a uniformly colored lambertian surface, the intensity of a point in the scene is the sum of 1-bounced ...
Fusing Multiview and Photometric Stereo for 3D Reconstruction under Uncalibrated Illumination
We propose a method to obtain a complete and accurate 3D model from multiview images captured under a variety of unknown illuminations. Based on recent results showing that for Lambertian objects, general illumination can be approximated well using low-...
Comments