Abstract
We present TensoRF, a novel approach to model and reconstruct radiance fields. Unlike NeRF that purely uses MLPs, we model the radiance field of a scene as a 4D tensor, which represents a 3D voxel grid with per-voxel multi-channel features. Our central idea is to factorize the 4D scene tensor into multiple compact low-rank tensor components. We demonstrate that applying traditional CANDECOMP/PARAFAC (CP) decomposition – that factorizes tensors into rank-one components with compact vectors – in our framework leads to improvements over vanilla NeRF. To further boost performance, we introduce a novel vector-matrix (VM) decomposition that relaxes the low-rank constraints for two modes of a tensor and factorizes tensors into compact vector and matrix factors. Beyond superior rendering quality, our models with CP and VM decompositions lead to a significantly lower memory footprint in comparison to previous and concurrent works that directly optimize per-voxel features. Experimentally, we demonstrate that TensoRF with CP decomposition achieves fast reconstruction (\(<30\) min) with better rendering quality and even a smaller model size (\(<4\) MB) compared to NeRF. Moreover, TensoRF with VM decomposition further boosts rendering quality and outperforms previous state-of-the-art methods, while reducing the reconstruction time (\(<10\) min) and retaining a compact model size (\(<75\) MB).
A. Chen and Z. Xu—Equal Contribution.
Research done when Anpei Chen was in a remote internship with UCSD.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ballester-Ripoll, R., Pajarola, R.: Tensor decomposition methods in visual computing. IEEE Vis. Tutorials 3 (2016)
Ben-Younes, H., Cadene, R., Thome, N., Cord, M.: BLOCK: bilinear superdiagonal fusion for visual question answering and visual relationship detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 8102–8109 (2019)
Bi, S., Xu, Z., et al.: Neural reflectance fields for appearance acquisition. arXiv preprint arXiv:2008.03824 (2020)
Bi, S., Xu, Z., et al.: Deep reflectance volumes: relightable reconstructions from multi-view photometric images. In: Proceedings ECCV, pp. 294–311 (2020)
Boss, M., Braun, R., Jampani, V., Barron, J.T., Liu, C., Lensch, H.: NeRD: neural reflectance decomposition from image collections. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 12684–12694 (2021)
Candes, E.J., Plan, Y.: Matrix completion with noise. Proc. IEEE 98(6), 925–936 (2010)
Carroll, J.D., Chang, J.J.: Analysis of individual differences in multidimensional scaling via an n-way generalization of “ckart-young" decomposition. Psychometrika 35(3), 283–319 (1970)
Chan, E.R., et al.: Efficient geometry-aware 3D generative adversarial networks. In: CVPR, pp. 16123–16133 (2022)
Chan, E.R., Monteiro, M., Kellnhofer, P., Wu, J., Wetzstein, G.: 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, pp. 5799–5809 (2021)
Chen, A.: Deep surface light fields. Proc. ACM Comput. Graph. Interact. Tech. 1(1), 1–17 (2018)
Chen, A., et al.: MVSNeRF: fast generalizable radiance field reconstruction from multi-view stereo. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 14124–14133 (2021)
Chibane, J., Bansal, A., Lazova, V., Pons-Moll, G.: Stereo radiance fields (SRF): learning view synthesis from sparse views of novel scenes. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7911–7920. IEEE (2021)
De Lathauwer, L.: Decompositions of a higher-order tensor in block terms-part ii: definitions and uniqueness. SIAM J. Matrix Anal. Appl. 30(3), 1033–1066 (2008)
Deng, H.: Constant-cost spatio-angular prefiltering of glinty appearance using tensor decomposition. ACM Trans. Graph. (TOG) 41(2), 1–17 (2022)
Dong, W., Shi, G., Li, X., Ma, Y., Huang, F.: Compressive sensing via nonlocal low-rank regularization. IEEE Trans. Image Process. 23(8), 3618–3632 (2014)
Gandy, S., Recht, B., Yamada, I.: Tensor completion and low-n-rank tensor recovery via convex optimization. Inverse Prob. 27(2), 025010 (2011)
Garbin, S.J., Kowalski, M., Johnson, M., Shotton, J., Valentin, J.: FastNeRF: high-fidelity neural rendering at 200FPS. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 14346–14355 (2021)
Groueix, T., Fisher, M., Kim, V.G., Russell, B.C., Aubry, M.: A papier-mâché approach to learning 3D surface generation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 216–224 (2018)
Harshman, R.A., et al.: Foundations of the PARAFAC procedure: models and conditions for an “explanatory" multimodal factor analysis (1970)
Hedman, P., Srinivasan, P.P., Mildenhall, B., Barron, J.T., Debevec, P.: Baking neural radiance fields for real-time view synthesis. arXiv preprint arXiv:2103.14645 (2021)
Ji, H., Liu, C., Shen, Z., Xu, Y.: Robust video denoising using low rank matrix completion. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1791–1798. IEEE (2010)
Ji, M., Gall, J., Zheng, H., Liu, Y., Fang, L.: SurfaceNet: an end-to-end 3D neural network for multiview stereopsis. In: Proceedings ICCV, pp. 2307–2315 (2017)
Ji, Y., Wang, Q., Li, X., Liu, J.: A survey on tensor techniques and applications in machine learning. IEEE Access 7, 162950–162990 (2019)
Kamal, M.H., Heshmat, B., Raskar, R., Vandergheynst, P., Wetzstein, G.: Tensor low-rank and sparse light field photography. Comput. Vis. Image Underst. 145, 172–181 (2016)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Knapitsch, A., Park, J., Zhou, Q.Y., Koltun, V.: Tanks and temples: benchmarking large-scale scene reconstruction. ACM Trans. Graph. 36(4), 1–13 (2017)
Kolda, T.G., Bader, B.W.: Tensor decompositions and applications. SIAM Rev. 51(3), 455–500 (2009)
Li, Z., Niklaus, S., Snavely, N., Wang, O.: Neural scene flow fields for space-time view synthesis of dynamic scenes. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6498–6508 (2021)
Liang, R., Sun, H., Vijaykumar, N.: CoordX: accelerating implicit neural representation with a split MLP architecture. arXiv preprint arXiv:2201.12425 (2022)
Liu, J., Musialski, P., Wonka, P., Ye, J.: Tensor completion for estimating missing values in visual data. IEEE Trans. Pattern Anal. Mach. Intell. 35(1), 208–220 (2012)
Liu, L., Gu, J., Lin, K.Z., Chua, T.S., Theobalt, C.: Neural sparse voxel fields. NeurIPS 33, 15651–15663 (2020)
Liu, S., Zhang, X., Zhang, Z., Zhang, R., Zhu, J.Y., Russell, B.: Editing conditional radiance fields. arXiv preprint arXiv:2105.06466 (2021)
Lombardi, S., Simon, T., Saragih, J., Schwartz, G., Lehrmann, A., Sheikh, Y.: Neural volumes: learning dynamic renderable volumes from images. ACM Trans. Graph. 38, 1–14 (2019)
Martin-Brualla, R., Radwan, N., Sajjadi, M.S., Barron, J.T., Dosovitskiy, A., Duckworth, D.: NeRF in the wild: neural radiance fields for unconstrained photo collections. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7210–7219 (2021)
Mescheder, L., Oechsle, M., Niemeyer, M., Nowozin, S., Geiger, A.: Occupancy networks: learning 3D reconstruction in function space. In: Proceedings CVPR, pp. 4460–4470 (2019)
Mildenhall, B., et al.: Local light field fusion: practical view synthesis with prescriptive sampling guidelines. ACM Trans. Graph. (TOG) 38(4), 1–14 (2019)
Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: NeRF: representing scenes as neural radiance fields for view synthesis. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 405–421. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58452-8_24
Müller, T., Evans, A., Schied, C., Keller, A.: Instant neural graphics primitives with a multiresolution hash encoding. ACM Trans. Graph. 41(4), 102:1-102:15 (2022)
Nam, G., Lee, J.H., Gutierrez, D., Kim, M.H.: Practical SVBRDF acquisition of 3D objects with unstructured flash photography. ACM Trans. Graph. (TOG) 37(6), 1–12 (2018)
Niemeyer, M., Geiger, A.: GIRAFFE: representing scenes as compositional generative neural feature fields. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11453–11464 (2021)
Oechsle, M., Peng, S., Geiger, A.: UNISURF: unifying neural implicit surfaces and radiance fields for multi-view reconstruction. In: International Conference on Computer Vision (ICCV), pp. 5589–5599 (2021)
Panagakis, Y.: Tensor methods in computer vision and deep learning. Proc. IEEE 109(5), 863–890 (2021)
Park, K., et al.: HyperNeRF: a higher-dimensional representation for topologically varying neural radiance fields. ACM Trans. Graph. 40(6), 1–12 (2021)
Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems 32 (2019)
Peng, S., Niemeyer, M., Mescheder, L., Pollefeys, M., Geiger, A.: Convolutional occupancy networks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12348, pp. 523–540. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58580-8_31
Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: deep learning on point sets for 3D classification and segmentation. In: Proceedings CVPR, pp. 652–660 (2017)
Qi, C.R., Su, H., Nießner, M., Dai, A., Yan, M., Guibas, L.J.: Volumetric and multi-view CNNs for object classification on 3D data. In: Proceedings CVPR, pp. 5648–5656 (2016)
Reiser, C., Peng, S., Liao, Y., Geiger, A.: KiloNeRF: speeding up neural radiance fields with thousands of tiny MLPs. In: International Conference on Computer Vision (ICCV), pp. 14335–14345 (2021)
Sara, F.K., Alex, Yu., Tancik, M., Chen, Q., Recht, B., Kanazawa, A.: Plenoxels: radiance fields without neural networks. In: CVPR, pp. 5501–5510 (2022)
Schwarz, K., Liao, Y., Niemeyer, M., Geiger, A.: GRAF: generative radiance fields for 3D-aware image synthesis. In: Advances in Neural Information Processing Systems (NeurIPS), pp. 20154–20166 (2020)
Sitzmann, V., Martel, J., Bergman, A., Lindell, D., Wetzstein, G.: Implicit neural representations with periodic activation functions. Adv. Neural. Inf. Process. Syst. 33, 7462–7473 (2020)
Sitzmann, V., Thies, J., Heide, F., Nießner, M., Wetzstein, G., Zollhofer, M.: DeepVoxels: learning persistent 3D feature embeddings. In: Proceedings CVPR, pp. 2437–2446 (2019)
Sitzmann, V., Zollhöfer, M., Wetzstein, G.: Scene representation networks: continuous 3D-structure-aware neural scene representations. In: Advances in Neural Information Processing Systems (2019)
Sun, C., Sun, M., Chen, H.T.: Direct voxel grid optimization: super-fast convergence for radiance fields reconstruction. arXiv preprint arXiv:2111.11215 (2021)
Tancik, M., et al.: Fourier features let networks learn high frequency functions in low dimensional domains. NeurIPS 33, 7537–7547 (2020)
Trevithick, A., Yang, B.: GRF: learning a general radiance field for 3D scene representation and rendering. In: arXiv:2010.04595 (2020)
Tucker, L.R.: Some mathematical notes on three-mode factor analysis. Psychometrika 31(3), 279–311 (1966)
Vasilescu, M.A.O., Terzopoulos, D.: TensorTextures: multilinear image-based rendering. In: ACM SIGGRAPH 2004 Papers, pp. 336–342 (2004)
Wang, J., Dong, Y., Tong, X., Lin, Z., Guo, B.: Kernel nyström method for light transport. In: ACM SIGGRAPH 2009 papers, pp. 1–10 (2009)
Wang, N., Zhang, Y., Li, Z., Fu, Y., Liu, W., Jiang, Y.G.: Pixel2Mesh: generating 3D mesh models from single RGB images. In: Proceedings ECCV, pp. 52–67 (2018). https://doi.org/10.1007/978-3-030-01252-6_4
Wang, P., Liu, L., Liu, Y., Theobalt, C., Komura, T., Wang, W.: NeuS: learning neural implicit surfaces by volume rendering for multi-view reconstruction. In: NeurIPS (2021)
Wang, Q., et al: Learning multi-view image-based rendering. In: CVPR, pp. 4690–4699 (2021)
Xiang, F., Xu, Z., Hasan, M., Hold-Geoffroy, Y., Sunkavalli, K., Su, H.: NeuTex: neural texture mapping for volumetric neural rendering. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7119–7128 (2021)
Xu, Q., Xu, Z., Philip, J., Bi, S., Shu, Z., Sunkavalli, K., Neumann, U.: Point-NeRF: point-based neural radiance fields. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5438–5448 (2022)
Ye, J., Li, G., Chen, D., Yang, H., Zhe, S., Xu, Z.: Block-term tensor neural networks. Neural Netw. 130, 11–21 (2020)
Ye, J., et al.: Learning compact recurrent neural networks with block-term tensor decomposition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9378–9387 (2018)
Yu, A., Li, R., Tancik, M., Li, H., Ng, R., Kanazawa, A.: PlenOctrees for real-time rendering of neural radiance fields. arXiv preprint arXiv:2103.14024 (2021)
Yu, A., Ye, V., Tancik, M., Kanazawa, A.: PixelNeRF: neural radiance fields from one or few images. In: CVPR, pp. 4578–4587 (2021)
Zhang, K., Riegler, G., Snavely, N., Koltun, V.: NeRF++: analyzing and improving neural radiance fields. arXiv preprint arXiv:2010.07492 (2020)
Zhou, T., Tucker, R., Flynn, J., Fyffe, G., Snavely, N.: Stereo magnification: learning view synthesis using multiplane images. ACM Trans. Graph. 37(4), 1–12 (2018)
Zhou, Z.: Sparse-as-possible SVBRDF acquisition. ACM Trans. Graph. (TOG) 35(6), 1–12 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Chen, A., Xu, Z., Geiger, A., Yu, J., Su, H. (2022). TensoRF: Tensorial Radiance Fields. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13692. Springer, Cham. https://doi.org/10.1007/978-3-031-19824-3_20
Download citation
DOI: https://doi.org/10.1007/978-3-031-19824-3_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-19823-6
Online ISBN: 978-3-031-19824-3
eBook Packages: Computer ScienceComputer Science (R0)