Neural Radiance Fields with Hash-Low-Rank Decomposition
Source abstract
Abstract
In recent advancements in novel view synthesis and neural rendering, neural radiance field (NeRF) has emerged as a powerful technique for synthesizing high-quality novel views of complex 3D scenes. However, the computational and storage demands of NeRF limit its applicability. In this paper, we present a novel approach to NeRF by combining low-rank decomposition and multi-hash encoding through a novel integration process to enhance efficiency and scalability. Our method reduces the model complexity and accelerates the training processes while maintaining high rendering quality. We demonstrate the effectiveness of our approach through extensive experiments on various datasets, showing significant improvements in performance and memory usage compared to traditional NeRF implementations. These results suggest that our approach can make NeRF more practical for real-world applications, such as virtual reality, gaming, and 3D reconstruction.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Medical Image Segmentation Techniques · Advanced Vision and Imaging · Neural Networks and Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Computer Science, Hangzhou Dianzi University, Hangzhou 310018, China
School of Engineering, Westlake University, Hangzhou 310012, China
Funding
National Science and Technology Innovation · National Natural Science Foundation of China · Zhejiang Provincial Natural Science Foundation of China · Key Research and Development Project of Zhejiang Province · Key Laboratory of Brain Machine Collaborative Intelligence of Zhejiang Province
References (22)
Show source-provided references
1. Achlioptas, P., Diamanti, O., Mitliagkas, I., and Guibas, L. (2018, January 10–15). Learning Representations and Generative Models for 3D Point Clouds. Proceedings of the International Conference on Machine Learning, Stockholm, Sweden.
2. Xu, Q., Xu, Z., Philip, J., Bi, S., Shu, Z., Sunkavalli, K., and Neumann, U. (2022, January 18–24). Point-nerf: Point-based neural radiance fields. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.10.1109/CVPR52688.2022.00536 ↗
3. Qi, C.R., Su, H., Mo, K., and Guibas, L.J. (2017, January 21–26). Pointnet: Deep learning on point sets for 3d classification and segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.
4. Sun, C., Sun, M., and Chen, H.T. (2022, January 18–24). Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction. Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.10.1109/CVPR52688.2022.00538 ↗
5. Fridovich-Keil, S., Yu, A., Tancik, M., Chen, Q., Recht, B., and Kanazawa, A. (2022, January 18–24). Plenoxels: Radiance fields without neural networks. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.10.1109/CVPR52688.2022.00542 ↗
6. Yu, A., Li, R., Tancik, M., Li, H., Ng, R., and Kanazawa, A. (2021, January 11–17). PlenOctrees for Real-time Rendering of Neural Radiance Fields. Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, BC, Canada.10.1109/ICCV48922.2021.00570 ↗
7. Sitzmann, V., Thies, J., Heide, F., Nießner, M., Wetzstein, G., and Zollhofer, M. (2019, January 15–20). Deepvoxels: Learning persistent 3d feature embeddings. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00254 ↗
8. Shewchuk, J.R. (1998, January 7–10). Tetrahedral mesh generation by Delaunay refinement. Proceedings of the Fourteenth Annual Symposium on Computational Geometry—SCG ’98, Minneapolis, MN, USA.10.1145/276884.276894 ↗
9. Wang, N., Zhang, Y., Li, Z., Fu, Y., Liu, W., and Jiang, Y.G. (2018). Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images. Computer Vision—ECCV 2018, Springer. Lecture Notes in Computer Science.10.1007/978-3-030-01252-6_4 ↗
10. Takikawa, T., Litalien, J., Yin, K., Kreis, K., Loop, C., Nowrouzezahrai, D., Jacobson, A., McGuire, M., and Fidler, S. (2021, January 20–25). Neural geometric level of detail: Real-time rendering with implicit 3d shapes. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.10.1109/CVPR46437.2021.01120 ↗
11. Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., and Ng, R. (2020, January 23–28). Nerf: Representing scenes as neural radiance fields for view synthesis. Proceedings of the European Conference on Computer Vision, Glasgow, UK.10.1007/978-3-030-58452-8_24 ↗
12. 3D Gaussian Splatting for Real-Time Radiance Field Rendering10.1145/3592433 ↗
13. Chen, A., Xu, Z., Geiger, A., Yu, J., and Su, H. (2022, January 23–27). Tensorf: Tensorial radiance fields. Proceedings of the European Conference on Computer Vision, Tel Aviv, Israel.10.1007/978-3-031-19824-3_20 ↗
14. Instant Neural Graphics Primitives with a Multiresolution Hash Encoding
15. Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields10.1109/TPAMI.2015.2505283 ↗
16. Tensor Decompositions and Applications10.1137/07070111X ↗
17. Tensor low-rank and sparse light field photography10.1016/j.cviu.2015.11.004 ↗
18. Teschner, M., Heidelberger, B., Müller, M., Pomerantes, D., and Gross, M. (2003). Optimized Spatial Hashing for Collision Detection of Deformable Objects. Vision Modeling and Visualization, Vision Modeling and Visualization, Korea University.
19. Tanks and Temples: Benchmarking Large-Scale Scene Reconstruction10.1145/3072959.3073599 ↗
20. Kingma, D., and Ba, J. (2014). Adam: A Method for Stochastic Optimization. arXiv.
21. Liu, L., Gu, J., Lin, K., Chua, T.S., and Theobalt, C. (2020). Neural Sparse Voxel Fields. arXiv.
22. Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., and Niessner, M. (2017, January 21–26). ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.261 ↗