Elamur Research⌕
☰
home / papers / 2023 / 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering

4D Gaussian Splatting for Real-Time Dynamic Scene Rendering

Paper · 2023 · Guanjun Wu, Taoran Yi, Jiemin Fang et al.

Summary

Rendering dynamic scenes from new viewpoints and timestamps is hard to do both accurately and quickly. NeRF-style methods remain slow at render time. The obvious extension of 3D Gaussian Splatting (3D-GS) is to fit separate Gaussians for every frame, as Dynamic3DGS does, but then storage grows with sequence length. The authors propose 4D Gaussian Splatting (4D-GS). It keeps one canonical set of 3D Gaussians and learns a Gaussian deformation field that shifts each Gaussian and alters its rotation and scale for a given timestamp. The field pairs a spatial-temporal structure encoder with a tiny MLP decoder. The encoder uses multi-resolution factorized voxel planes inspired by HexPlane. The decoder has separate heads for position, rotation and scaling. Nearby Gaussians read shared plane features, so their motions are coupled rather than learned in isolation. The deformed Gaussians are drawn with ordinary differentiable splatting. 4D-GS runs in real time (82 FPS at 800×800 on an RTX 3090) and matches or beats earlier state-of-the-art quality. Its memory depends only on the number of Gaussians plus the network size.

Key points

  • Reported speed is up to 82 FPS at 800×800 on synthetic data and 30 FPS at 1352×1014 on real data, measured on a single RTX 3090.
  • Memory cost is O(N + F), meaning the number of Gaussians plus the deformation network parameters. Per-timestamp tables as in Dynamic3DGS cost O(tN).
  • The full model scores PSNR 34.05 dB, SSIM 0.98 and LPIPS 0.02 on the synthetic-data ablation, with about 8 minutes of training and 18 MB of storage.
  • Ablations show which parts matter:
    • Removing the HexPlane encoder cuts PSNR to 27.05, although training is faster (4 mins, 140 FPS).
    • Skipping the static initialization gives 31.91.
    • Dropping the position head gives 26.67.
    • Dropping the rotation or scaling head costs about 1 dB each.
  • Stated limitations:
    • Large motions, missing background points and inaccurate camera poses make optimization difficult.
    • Static and dynamic parts are hard to separate in monocular input.
    • Urban-scale scenes are too costly, because so many Gaussians must query the deformation field.

Interesting ideas

  • I1. One canonical set plus a learned deformation. Storing a single base representation and a compact time-conditioned network avoids duplicating state per frame. The same pattern suits any time-varying data where storage would otherwise grow with sequence length.
  • I2. Shared factorized features for neighbours. Gaussians are encoded through multi-resolution 2D planes (xy, xz, yz and their pairings with t), so neighbouring elements share information. This regularizes their behaviour and avoids tearing artifacts. Low-rank plane factorization is a cheap way to give local smoothness to any set of points indexed by coordinates.
  • I3. Separate small heads for separate attributes. Splitting the decoder into position, rotation and scaling heads lets the ablation measure each one's contribution. In this paper, position turned out to matter most.
  • I4. Static warm-up before joint training. The Gaussians are first fitted as a static scene for the first few thousand iterations, and only then is the deformation field trained jointly. Starting with the simpler subproblem before adding the time dimension is a general curriculum trick for stabilizing optimization.
  • I5. Treating speed as a budget, not a single number. The authors relate FPS to the Gaussian count, noting up to 90 FPS below 30,000 Gaussians. They also state that resolution, scene complexity and network capacity all have to be balanced. Reporting such trade-off curves alongside headline numbers is a sound evaluation habit.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🏢Huawei TechnologiesShenzhen · China96 works · 15,432 citations🎓Huazhong University of Science and TechnologyWuhan · China59 works · 8,310 citations

 Fields, topics and concepts

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 18,614 worksComputer Vision and Pattern Recognition · 3,486 worksEngineering · 188 worksComputer Graphics and Computer-Aided Design · 16 worksComputational Mechanics · 5 works

Cite

Cite as Guanjun Wu, Taoran Yi, Jiemin Fang, Lingxi Xie, Xiaopeng Zhang, Wei Wei, Wenyu Liu, Qi Tian and Xinggang Wang. 2023. 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering. arXiv:2310.08528.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.2310.08528 · arXiv 2310.08528

@misc{wu20234d,
  title = {{4D Gaussian Splatting for Real-Time Dynamic Scene Rendering}},
  author = {Guanjun Wu, Taoran Yi, Jiemin Fang, Lingxi Xie, Xiaopeng Zhang, Wei Wei, Wenyu Liu, Qi Tian and Xinggang Wang},
  year = {2023},
  doi = {10.48550/arxiv.2310.08528},
  eprint = {2310.08528},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2310.08528}
}

References

68 references, 3 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Jad Abou-Chakra, Feras Dayoub, and Niko Sünderhauf. Par-ticlenerf: Particle based encoding for online neural radiance fields in dynamic scenes. arXiv preprint arXiv:2211.04041, 2022. 3, 15 — [arXiv:2211.04041](https://arxiv.org/abs/2211.04041) find
  2. Benjamin Attal, Jia-Bin Huang, Christian Richardt, Michael Zollhoefer, Johannes Kopf, Matthew O’Toole, and Changil Kim. Hyperreel: High-fidelity 6-dof video with ray-conditioned sampling. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 16610–16620, 2023. 5… find
  3. Jonathan T Barron, Ben Mildenhall, Matthew Tancik, Peter Hedman, Ricardo Martin-Brualla, and Pratul P Srinivasan. Mip-nerf: A multiscale representation for anti-aliasing neural radiance fields. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 5855–5864, 2021. 2 find
  4. Michael Broxton, John Flynn, Ryan Overbeck, Daniel Erickson, Peter Hedman, Matthew Duvall, Jason Dourgarian, Jay Busch, Matt Whalen, and Paul Debevec. Immersive light field video with a layered mesh representation. ACM Transactions on Graphics (TOG), 39(4):86–1, 2020. 2 find
  5. Ang Cao and Justin Johnson. Hexplane: A fast representation for dynamic scenes. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 130–141, 2023. 1, 2, 4, 5, 6, 7, 13, 14 find
  6. Guikun Chen and Wenguan Wang. A survey on 3d gaussian splatting. arXiv preprint arXiv:2401.03890, 2024. 3 — [arXiv:2401.03890](https://arxiv.org/abs/2401.03890) find
  7. Alvaro Collet, Ming Chuang, Pat Sweeney, Don Gillett, Dennis Evseev, David Calabrese, Hugues Hoppe, Adam Kirk, and Steve Sullivan. High-quality streamable free-viewpoint video. ACM Transactions on Graphics (ToG), 34(4):1–13, 2015. 2 find
  8. Robert A Drebin, Loren Carpenter, and Pat Hanrahan. Volume rendering. ACM Siggraph Computer Graphics, 22(4): 65–74, 1988. 1 find
  9. Jiemin Fang, Taoran Yi, Xinggang Wang, Lingxi Xie, Xiaopeng Zhang, Wenyu Liu, Matthias Nießner, and Qi Tian. Fast dynamic radiance fields with time-aware neural voxels. In SIGGRAPH Asia 2022 Conference Papers, pages 1–9, 2022. 1, 2, 4, 5, 6, 7, 12, 13, 14, 15 find
  10. John Flynn, Michael Broxton, Paul Debevec, Matthew Du-Vall, Graham Fyffe, Ryan Overbeck, Noah Snavely, and Richard Tucker. Deepview: View synthesis with learned gradient descent. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2367– 2376, 2019. 2 find
  11. Sara Fridovich-Keil, Alex Yu, Matthew Tancik, Qinhong Chen, Benjamin Recht, and Angjoo Kanazawa. Plenoxels: Radiance fields without neural networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5501–5510, 2022. 1, 3 find
  12. Sara Fridovich-Keil, Giacomo Meanti, Frederik Rahbæk Warburg, Benjamin Recht, and Angjoo Kanazawa. K-planes: Explicit radiance fields in space, time, and appearance. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 12479–12488, 2023. 1, 2, 4, 5, 6, 7, 13, 1… find
  13. Wanshui Gan, Hongbin Xu, Yi Huang, Shifeng Chen, and Naoto Yokoya. V4d: Voxel for 4d novel view synthesis. IEEE Transactions on Visualization and Computer Graphics, 2023. 2, 6, 7 find
  14. Chen Gao, Ayush Saraf, Johannes Kopf, and Jia-Bin Huang. Dynamic view synthesis from dynamic monocular video. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 5712–5721, 2021. 2 find
  15. Hang Gao, Ruilong Li, Shubham Tulsiani, Bryan Russell, and Angjoo Kanazawa. Monocular dynamic view synthesis: A reality check. Advances in Neural Information Processing Systems, 35:33768–33780, 2022. 14 find
  16. Xiangjun Gao, Jiaolong Yang, Jongyoo Kim, Sida Peng, Zicheng Liu, and Xin Tong. Mps-nerf: Generalizable 3d human rendering from multiview images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022. 2 find
  17. Kaiwen Guo, Feng Xu, Yangang Wang, Yebin Liu, and Qionghai Dai. Robust non-rigid motion tracking and surface reconstruction using l0 regularization. In Proceedings of the IEEE International Conference on Computer Vision, pages 3083–3091, 2015. 2 find
  18. Kaiwen Guo, Peter Lincoln, Philip Davidson, Jay Busch, Xueming Yu, Matt Whalen, Geoff Harvey, Sergio Orts-Escolano, Rohit Pandey, Jason Dourgarian, et al. The relightables: Volumetric performance capture of humans with realistic relighting. ACM Transactions on Graphics (ToG), 38(6):1–19, 2019. 2 find
  19. Xiang Guo, Jiadai Sun, Yuchao Dai, Guanying Chen, Xiaoqing Ye, Xiao Tan, Errui Ding, Yumeng Zhang, and Jingdong Wang. Forward flow for novel view synthesis of dynamic scenes. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 16022–16033, 2023. 2, 5, 6, 7, 12 find
  20. Tao Hu, Tao Yu, Zerong Zheng, He Zhang, Yebin Liu, and Matthias Zwicker. Hvtr: Hybrid volumetric-textural rendering for human avatars. In 2022 International Conference on 3D Vision (3DV), pages 197–208. IEEE, 2022. 2 find
  21. Hanbyul Joo, Hao Liu, Lei Tan, Lin Gui, Bart Nabbe, Iain Matthews, Takeo Kanade, Shohei Nobuhara, and Yaser Sheikh. Panoptic studio: A massively multiview system for social motion capture. In Proceedings of the IEEE International Conference on Computer Vision, pages 3334–3342, 2015. 14, 15 find
  22. Bernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, and George Drettakis. 3d gaussian splatting for real-time radiance field rendering. ACM Transactions on Graphics (ToG), 42(4):1–14, 2023. 1, 3, 4, 5, 6, 7, 11, 12, 14 find
  23. Leonid Keselman and Martial Hebert. Approximate differentiable rendering with algebraic surfaces. In European Conference on Computer Vision, pages 596–614. Springer, 2022. 3 find
  24. Leonid Keselman and Martial Hebert. Flexible techniques for differentiable rendering with 3d gaussians. arXiv preprint arXiv:2308.14737, 2023. 3 find
  25. Tianye Li, Mira Slavcheva, Michael Zollhoefer, Simon Green, Christoph Lassner, Changil Kim, Tanner Schmidt, Steven Lovegrove, Michael Goesele, Richard Newcombe, et al. Neural 3d video synthesis from multi-view video. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognitio… find
  26. Zhong Li, Yu Ji, Wei Yang, Jinwei Ye, and Jingyi Yu. Robust 3d human motion reconstruction via dynamic template construction. In 2017 International Conference on 3D Vision (3DV), pages 496–505. IEEE, 2017. 2 find
  27. Zhong Li, Minye Wu, Wangyiteng Zhou, and Jingyi Yu. 4d human body correspondences from panoramic depth maps. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 2877–2886, 2018. 2 find
  28. Zhengqi Li, Simon Niklaus, Noah Snavely, and Oliver Wang. 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, pages 6498– 6508, 2021. 2 find
  29. Zhan Li, Zhang Chen, Zhong Li, and Yi Xu. Spacetime gaussian feature splatting for real-time dynamic view synthesis. arXiv preprint arXiv:2312.16812, 2023. 3 find
  30. Haotong Lin, Sida Peng, Zhen Xu, Tao Xie, Xingyi He, Hujun Bao, and Xiaowei Zhou. High-fidelity and real-time novel view synthesis for dynamic scenes. In SIGGRAPH Asia Conference Proceedings, 2023. 2, 5, 6, 7, 9, 15 find
  31. Xingyu Liu, Mengyuan Yan, and Jeannette Bohg. Meteor-net: Deep learning on dynamic 3d point cloud sequences. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 9246–9255, 2019. 3 find
  32. Yu-Lun Liu, Chen Gao, Andreas Meuleman, Hung-Yu Tseng, Ayush Saraf, Changil Kim, Yung-Yu Chuang, Johannes Kopf, and Jia-Bin Huang. Robust dynamic radiance fields. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13–23, 2023. 2 find
  33. Jonathon Luiten, Georgios Kopanas, Bastian Leibe, and Deva Ramanan. Dynamic 3d gaussians: Tracking by persistent dynamic view synthesis. In 3DV, 2024. 2, 3, 7, 14, 15 find
  34. Ricardo Martin-Brualla, Noha Radwan, Mehdi SM Sajjadi, Jonathan T Barron, Alexey Dosovitskiy, and Daniel Duckworth. Nerf in the wild: Neural radiance fields for unconstrained photo collections. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7210–7219, 202… find
  35. Ben Mildenhall, Pratul P Srinivasan, Matthew Tancik, Jonathan T Barron, Ravi Ramamoorthi, and Ren Ng. Nerf: Representing scenes as neural radiance fields for view synthesis. Communications of the ACM, 65(1):99–106, 2021. 1, 2, 3 find
  36. Thomas Müller, Alex Evans, Christoph Schied, and Alexander Keller. Instant neural graphics primitives with a multiresolution hash encoding. ACM Transactions on Graphics (ToG), 41(4):1–15, 2022. 1, 3
  37. Byeongjun Park and Changick Kim. Point-dynrf: Point-based dynamic radiance fields from a monocular video. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 3171–3181, 2024. 3 find
  38. Keunhong Park, Utkarsh Sinha, Jonathan T Barron, Sofien Bouaziz, Dan B Goldman, Steven M Seitz, and Ricardo Martin-Brualla. Nerfies: Deformable neural radiance fields. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 5865–5874, 2021. 2, 6, 7, 12 find
  39. Keunhong Park, Utkarsh Sinha, Peter Hedman, Jonathan T Barron, Sofien Bouaziz, Dan B Goldman, Ricardo Martin-Brualla, and Steven M Seitz. Hypernerf: A higher-dimensional representation for topologically varying neural radiance fields. arXiv preprint arXiv:2106.13228, 2021. 2, 4, 6, 7, 12, 13, 14, 15 — [arXiv:2106.13228](https://arxiv.org/abs/2106.13228) find
  40. Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, 32, 2019. 5
  41. Sida Peng, Yunzhi Yan, Qing Shuai, Hujun Bao, and Xiaowei Zhou. Representing volumetric videos as dynamic mlp maps. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4252– 4262, 2023. 2 find
  42. Albert Pumarola, Enric Corona, Gerard Pons-Moll, and Francesc Moreno-Noguer. D-nerf: Neural radiance fields for dynamic scenes. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 10318–10327, 2021. 1, 2, 5, 6, 12, 15 find
  43. Charles R Qi, Hao Su, Kaichun Mo, and Leonidas J Guibas. Pointnet: Deep learning on point sets for 3d classification and segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 652–660, 2017. 3 find
  44. Charles Ruizhongtai Qi, Li Yi, Hao Su, and Leonidas J Guibas. Pointnet++: Deep hierarchical feature learning on point sets in a metric space. Advances in neural information processing systems, 30, 2017. 3 find
  45. Darius Rückert, Linus Franke, and Marc Stamminger. Adop: Approximate differentiable one-pixel point rendering. ACM Transactions on Graphics (ToG), 41(4):1–14, 2022. 3 find
  46. Johannes L Schonberger and Jan-Michael Frahm. Structure-from-motion revisited. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4104–4113, 2016. 5, 6, 7 find
  47. Johannes L Schonberger and Jan-Michael Frahm. Structure-from-motion revisited. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4104–4113, 2016. 12 find
  48. Ruizhi Shao, Zerong Zheng, Hanzhang Tu, Boning Liu, Hongwen Zhang, and Yebin Liu. Tensor4d: Efficient neural 4d decomposition for high-fidelity dynamic reconstruction and rendering. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 16632– 16642, 2023. 1, 2,… find
  49. Liangchen Song, Anpei Chen, Zhong Li, Zhang Chen, Lele Chen, Junsong Yuan, Yi Xu, and Andreas Geiger. Nerfplayer: A streamable dynamic scene representation with decomposed neural radiance fields. IEEE Transactions on Visualization and Computer Graphics, 29(5):2732–2742, 2023. 5, 6, 7, 13 find
  50. Zhuo Su, Lan Xu, Zerong Zheng, Tao Yu, Yebin Liu, and Lu Fang. Robustfusion: Human volumetric capture with data-driven visual cues using a rgbd camera. In Computer Vision– ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part IV 16, pages 246–264. Springer, 2020. 2 find
  51. Cheng Sun, Min Sun, and Hwann-Tzong Chen. Direct voxel grid optimization: Super-fast convergence for radiance fields reconstruction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5459– 5469, 2022. 1, 3, 5
  52. Fengrui Tian, Shaoyi Du, and Yueqi Duan. Monon-erf: Learning a generalizable dynamic radiance field from monocular videos. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 17903–17913, 2023. 2 find
  53. Feng Wang, Zilong Chen, Guokang Wang, Yafei Song, and Huaping Liu. Masked space-time hash encoding for efficient dynamic scene reconstruction. Advances in neural information processing systems, 2023. 2, 5, 6, 7 find
  54. Feng Wang, Sinan Tan, Xinghang Li, Zeyue Tian, Yafei Song, and Huaping Liu. Mixed neural voxels for fast multi-view video synthesis. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 19706– 19716, 2023. 2, 5, 13 find
  55. Qianqian Wang, Zhicheng Wang, Kyle Genova, Pratul P Srinivasan, Howard Zhou, Jonathan T Barron, Ricardo Martin-Brualla, Noah Snavely, and Thomas Funkhouser. Ibrnet: Learning multi-view image-based rendering. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages… find
  56. Yiming Wang, Qin Han, Marc Habermann, Kostas Daniilidis, Christian Theobalt, and Lingjie Liu. Neus2: Fast learning of neural implicit surfaces for multi-view reconstruction. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 3295–3306, 2023. 2 find
  57. Zhou Wang, Alan C Bovik, Hamid R Sheikh, and Eero P Simoncelli. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing, 13(4):600–612, 2004. 6 find
  58. Qingshan Xu, Weihang Kong, Wenbing Tao, and Marc Pollefeys. Multi-scale geometric consistency guided and planar prior assisted multi-view stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(4):4945–4963, 2022. 2 find
  59. Qiangeng Xu, Zexiang Xu, Julien Philip, Sai Bi, Zhixin Shu, Kalyan Sunkavalli, and Ulrich Neumann. Point-nerf: Point-based neural radiance fields. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5438–5448, 2022. 3 find
  60. Ziyi Yang, Xinyu Gao, Wen Zhou, Shaohui Jiao, Yuqing Zhang, and Xiaogang Jin. Deformable 3d gaussians for high-fidelity monocular dynamic scene reconstruction. arXiv preprint arXiv:2309.13101, 2023. 3, 6 find
  61. Zeyu Yang, Hongye Yang, Zijie Pan, Xiatian Zhu, and Li Zhang. Real-time photorealistic dynamic scene representation and rendering with 4d gaussian splatting. arXiv preprint arXiv:2310.10642, 2023. 2, 3 — [arXiv:2310.10642](https://arxiv.org/abs/2310.10642) find
  62. Taoran Yi, Jiemin Fang, Xinggang Wang, and Wenyu Liu. Generalizable neural voxels for fast human radiance fields. arXiv preprint arXiv:2303.15387, 2023. 2 — [arXiv:2303.15387](https://arxiv.org/abs/2303.15387) find
  63. Wang Yifan, Felice Serena, Shihao Wu, Cengiz Öztireli, and Olga Sorkine-Hornung. Differentiable surface splatting for point-based geometry processing. ACM Transactions on Graphics (TOG), 38(6):1–14, 2019. 2, 3, 4, 7 find
  64. Lequan Yu, Xianzhi Li, Chi-Wing Fu, Daniel Cohen-Or, and Pheng-Ann Heng. Pu-net: Point cloud upsampling network. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2790–2799, 2018. 3 find
  65. Kai Zhang, Gernot Riegler, Noah Snavely, and Vladlen Koltun. Nerf++: Analyzing and improving neural radiance fields. arXiv preprint arXiv:2010.07492, 2020. 2 — [arXiv:2010.07492](https://arxiv.org/abs/2010.07492) find
  66. Richard Zhang, Phillip Isola, Alexei A Efros, Eli Shechtman, and Oliver Wang. The unreasonable effectiveness of deep features as a perceptual metric. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 586–595, 2018. 6 find
  67. Kaichen Zhou, Jia-Xing Zhong, Sangyun Shin, Kai Lu, Yiyuan Yang, Andrew Markham, and Niki Trigoni. Dyn-point: Dynamic neural point for view synthesis. Advances in Neural Information Processing Systems, 36, 2024. 2, 3 find
  68. Matthias Zwicker, Hanspeter Pfister, Jeroen Van Baar, and Markus Gross. Surface splatting. In Proceedings of the 28th annual conference on Computer graphics and interactive techniques, pages 371–378, 2001. 3 find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/wu-2023-4d-gaussian-splatting-real-time/