CoChat
Sign Up
Cited by 2483D Shape Modeling and AnalysisAdvanced Vision and ImagingComputer Graphics and Visualization Techniques

DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes

Open access
Zhou, Xiaoyu, Lin, Zhiwei, Shan, Xiaojun, Wang, Yongtao, Sun, Deqing, Yang, Ming-Hsuan·2024·2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
DOI 10.1109/cvpr52733.2024.02044
Open this paper in CoChat — free accountOpen PDF

Abstract

We present DrivingGaussian, an efficient and effective framework for surrounding dynamic autonomous driving scenes. For complex scenes with moving objects, we first sequentially and progressively model the static background of the entire scene with incremental static 3D Gaussians. We then leverage a composite dynamic Gaussian graph to handle multiple moving objects, individually reconstructing each object and restoring their accurate positions and occlusion relationships within the scene. We further use a LiDAR prior for Gaussian Splatting to reconstruct scenes with greater details and maintain panoramic consistency. DrivingGaussian outperforms existing methods in dynamic driving scene reconstruction and enables photorealistic surround-view synthesis with high-fidelity and multi-camera consistency. Our project page is at: https:/github.com/VDIGPKU/DrivingGaussian.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/cvpr52733.2024.02044

Cites

4 of 4 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • 3D scene reconstruction has been significantly improved with the use of generative models such as diffusion model-based SceneDiffuser and Gaussian splitting-based Drivinggaussian.

    “Recently, 3D scene reconstruction has been significantly improved with the use of generative models, such as the diffusion model-based SceneDiffuser [56] and the Gaussian splitting-based Drivinggaussian [57].”

    From Orchestrating Joint Offloading and Scheduling for Low-Latency Edge SLAM (2025) · cites this paper as [56]

    The Abstract (p. 1) reports that DrivingGaussian outperforms existing methods in dynamic driving-scene reconstruction, supporting the improvement attributed to it. But the Introduction (p. 2) describes its method as Composite Gaussian Splatting, not Gaussian splitting, and does not identify it as a generative model. This source does not establish the separate claim about SceneDiffuser. (LLM, conf=0.89)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 50

  1. [1][1] 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 ICCV , pages 5855-5864, 2021. 3, 7, 2 -
  2. [2][2] Jonathan T Barron, Ben Mildenhall, Dor Verbin, Pratul P Srinivasan, and Peter Hedman. Mip-nerf 360: Unbounded anti-aliased neural radiance fields. In CVPR , pages 54705479, 2022. 3, 7, 2, 4 -
  3. [3][3] Wenjing Bian, Zirui Wang, Kejie Li, Jia-Wang Bian, and Victor Adrian Prisacariu. Nope-nerf: Optimising neural radiance field with no pose prior. In CVPR , pages 4160-4169, 2023. 3 -
  4. [5][5] Holger Caesar, Juraj Kabzan, Kok Seang Tan, Whye Kit Fong, Eric Wolff, Alex Lang, Luke Fletcher, Oscar Beijbom, and Sammy Omari. nuplan: A closed-loop ml-based planning benchmark for autonomous vehicles. arXiv preprint arXiv:2106.11810 , 2021. 2 - · arXiv
  5. [6][6] Qi Cai, Yingwei Pan, Ting Yao, Chong-Wah Ngo, and Tao Mei. Objectfusion: Multi-modal 3d object detection with object-centric fusion. In ICCV , pages 18067-18076, 2023. 2 -
  6. [7][7] Xuanyao Chen, Tianyuan Zhang, Yue Wang, Yilun Wang, and Hang Zhao. Futr3d: A unified sensor fusion framework for 3d detection. In CVPR , pages 172-181, 2023. 2 -
  7. [8][8] Sara Fridovich-Keil, Alex Yu, Matthew Tancik, Qinhong Chen, Benjamin Recht, and Angjoo Kanazawa. Plenoxels: 9. Radiance fields without neural networks. In CVPR , pages 5501-5510, 2022. 3 -
  8. [9][9] Stephan J Garbin, Marek Kowalski, Matthew Johnson, Jamie Shotton, and Julien Valentin. Fastnerf: High-fidelity neural rendering at 200fps. In ICCV , pages 14346-14355, 2021. 3 -
  9. [10][10] Jianfei Guo, Nianchen Deng, Xinyang Li, Yeqi Bai, Botian Shi, Chiyu Wang, Chenjing Ding, Dongliang Wang, and Yikang Li. Streetsurf: Extending multi-view implicit surface reconstruction to street views. arXiv preprint arXiv:2306.04988 , 2023. 3 - · arXiv
  10. [11][11] Quentin Herau, Nathan Piasco, Moussab Bennehar, Luis Roldao, Dzmitry Tsishkou, Cyrille Migniot, Pascal Vasseur, and Cedric Demonceaux. Moisst: Multi-modal optimization of implicit scene for spatiotemporal calibration. arXiv preprint arXiv:2303.03056 , 2023. 5 - · arXiv
  11. [12][12] Xin Huang, Qi Zhang, Ying Feng, Hongdong Li, Xuan Wang, and Qing Wang. Hdr-nerf: High dynamic range neural radiance fields. In CVPR , pages 18398-18408, 2022. 3 -
  12. [14][14] Abhijit Kundu, Kyle Genova, Xiaoqi Yin, Alireza Fathi, Caroline Pantofaru, Leonidas J Guibas, Andrea Tagliasacchi, Frank Dellaert, and Thomas Funkhouser. Panoptic neural fields: A semantic object-aware neural scene representation. In CVPR , pages 12871-12881, 2022. 3, 4 -
  13. [15][15] Yuan Li, Zhi-Hao Lin, David Forsyth, Jia-Bin Huang, and Shenlong Wang. Climatenerf: Extreme weather synthesis in neural radiance field. In ICCV , pages 3227-3238, 2023. 3 -
  14. [16][16] Zhiqi Li, Wenhai Wang, Hongyang Li, Enze Xie, Chonghao Sima, Tong Lu, Yu Qiao, and Jifeng Dai. Bevformer: Learning bird's-eye-view representation from multi-camera images via spatiotemporal transformers. In ECCV , pages 118, 2022. 2 -
  15. [17][17] Tingting Liang, Hongwei Xie, Kaicheng Yu, Zhongyu Xia, Zhiwei Lin, Yongtao Wang, Tao Tang, Bing Wang, and Zhi Tang. Bevfusion: A simple and robust lidar-camera fusion framework. NeurIPS , pages 10421-10434, 2022. 2 -
  16. [19][19] Chen-Hsuan Lin, Wei-Chiu Ma, Antonio Torralba, and Simon Lucey. Barf: Bundle-adjusting neural radiance fields. In ICCV , pages 5741-5751, 2021. 3 -
  17. [20][20] 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 CVPR , pages 13-23, 2023. 3 -
  18. [21][21] Zhijian Liu, Haotian Tang, Alexander Amini, Xinyu Yang, Huizi Mao, Daniela L Rus, and Song Han. Bevfusion: Multitask multi-sensor fusion with unified bird's-eye view representation. In ICRA . IEEE, 2023. 2 -
  19. [22][22] Fan Lu, Yan Xu, Guang Chen, Hongsheng Li, Kwan-Yee Lin, and Changjun Jiang. Urban radiance field representation with deformable neural mesh primitives. In ICCV , pages 465-476, 2023. 7, 3, 4 -
  20. [23][23] Jonathon Luiten, Georgios Kopanas, Bastian Leibe, and Deva Ramanan. Dynamic 3d gaussians: Tracking by persistent dynamic view synthesis. arXiv preprint arXiv:2308.09713 , 2023. 2, 4 - · arXiv
  21. [24][24] 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 CVPR , pages 7210-7219, 2021. 3 -
  22. [25][25] Andreas Meuleman, Yu-Lun Liu, Chen Gao, Jia-Bin Huang, Changil Kim, Min H Kim, and Johannes Kopf. Progressively optimized local radiance fields for robust view synthesis. In CVPR , pages 16539-16548, 2023. 3 -
  23. [26][26] 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 , 2021. 2, 7, 4 -
  24. [27][27] Thomas M¨ uller, Alex Evans, Christoph Schied, and Alexander Keller. Instant neural graphics primitives with a multiresolution hash encoding. TOG , pages 1-15, 2022. 3, 7, 2 -
  25. [28][28] Julian Ost, Fahim Mannan, Nils Thuerey, Julian Knodt, and Felix Heide. Neural scene graphs for dynamic scenes. In CVPR , pages 2856-2865, 2021. 2, 3, 7, 4 -
  26. [29][29] Albert Pumarola, Enric Corona, Gerard Pons-Moll, and Francesc Moreno-Noguer. D-nerf: Neural radiance fields for dynamic scenes. In CVPR , pages 10318-10327, 2021. 3 -
  27. [30][30] Konstantinos Rematas, Andrew Liu, Pratul P Srinivasan, Jonathan T Barron, Andrea Tagliasacchi, Thomas Funkhouser, and Vittorio Ferrari. Urban radiance fields. In CVPR , pages 12932-12942, 2022. 7, 2 -
  28. [31][31] Tianhe Ren, Shilong Liu, Ailing Zeng, Jing Lin, Kunchang Li, He Cao, Jiayu Chen, Xinyu Huang, Yukang Chen, Feng Yan, Zhaoyang Zeng, Hao Zhang, Feng Li, Jie Yang, Hongyang Li, Qing Jiang, and Lei Zhang. Grounded sam: Assembling open-world models for diverse visual tasks. arXiv preprint arXiv:2401.14159 , 2024. 4, 2 - · arXiv
  29. [32][32] Viktor Rudnev, Mohamed Elgharib, William Smith, Lingjie Liu, Vladislav Golyanik, and Christian Theobalt. Nerf for outdoor scene relighting. In ECCV , pages 615-631, 2022. 3 -
  30. [33][33] Aron Schmied, Tobias Fischer, Martin Danelljan, Marc Pollefeys, and Fisher Yu. R3d3: Dense 3d reconstruction of dynamic scenes from multiple cameras. In ICCV , pages 3216-3226, 2023. 5 -
  31. [34][34] Johannes L Schonberger and Jan-Michael Frahm. Structurefrom-motion revisited. In CVPR , pages 4104-4113, 2016. 2, 5, 8 -
  32. [35][35] Yeji Song, Chaerin Kong, Seoyoung Lee, Nojun Kwak, and Joonseok Lee. Towards efficient neural scene graphs by learning consistency fields. arXiv preprint arXiv:2210.04127 , 2022. 2, 3 - · arXiv
  33. [36][36] Matthew Tancik, Vincent Casser, Xinchen Yan, Sabeek Pradhan, Ben Mildenhall, Pratul P Srinivasan, Jonathan T Barron, and Henrik Kretzschmar. Block-nerf: Scalable large scene neural view synthesis. In CVPR , pages 8248-8258, 2022. 2, 3 -
  34. [37][37] Siyu Teng, Xuemin Hu, Peng Deng, Bai Li, Yuchen Li, Yunfeng Ai, Dongsheng Yang, Lingxi Li, Zhe Xuanyuan, 16. Fenghua Zhu, et al. Motion planning for autonomous driving: The state of the art and future perspectives. IEEE Transactions on Intelligent Vehicles , 2023. 2 -
  35. [38][38] Haithem Turki, Deva Ramanan, and Mahadev Satyanarayanan. Mega-nerf: Scalable construction of large-scale nerfs for virtual fly-throughs. In CVPR , pages 12922-12931, 2022. 2, 3 -
  36. [39][39] Haithem Turki, Jason Y Zhang, Francesco Ferroni, and Deva Ramanan. Suds: Scalable urban dynamic scenes. In CVPR , pages 12375-12385, 2023. 3, 7, 2, 4 -
  37. [40][40] Qianqian Wang, Yen-Yu Chang, Ruojin Cai, Zhengqi Li, Bharath Hariharan, Aleksander Holynski, and Noah Snavely. Tracking everything everywhere all at once. arXiv preprint arXiv:2306.05422 , 2023. 2 - · arXiv
  38. [41][41] Zirui Wang, Shangzhe Wu, Weidi Xie, Min Chen, and Victor Adrian Prisacariu. Nerf-: Neural radiance fields without known camera parameters. arXiv preprint arXiv:2102.07064 , 2021. 3 - · arXiv
  39. [42][42] Zian Wang, Tianchang Shen, Jun Gao, Shengyu Huang, Jacob Munkberg, Jon Hasselgren, Zan Gojcic, Wenzheng Chen, and Sanja Fidler. Neural fields meet explicit geometric representations for inverse rendering of urban scenes. In CVPR , pages 8370-8380, 2023. 2, 3 -
  40. [43][43] Guanjun Wu, Taoran Yi, Jiemin Fang, Lingxi Xie, Xiaopeng Zhang, Wei Wei, Wenyu Liu, Qi Tian, and Xinggang Wang. 4d gaussian splatting for real-time dynamic scene rendering. arXiv preprint arXiv:2310.08528 , 2023. 2, 3 - · arXiv
  41. [44][44] Zirui Wu, Tianyu Liu, Liyi Luo, Zhide Zhong, Jianteng Chen, Hongmin Xiao, Chao Hou, Haozhe Lou, Yuantao Chen, Runyi Yang, et al. Mars: An instance-aware, modular and realistic simulator for autonomous driving. arXiv preprint arXiv:2307.15058 , 2023. 3 - · arXiv
  42. [45][45] Zeke Xie, Xindi Yang, Yujie Yang, Qi Sun, Yixiang Jiang, Haoran Wang, Yunfeng Cai, and Mingming Sun. S3im: Stochastic structural similarity and its unreasonable effectiveness for neural fields. In ICCV , pages 18024-18034, 2023. 6 -
  43. [46][46] Ziyang Xie, Junge Zhang, Wenye Li, Feihu Zhang, and Li Zhang. S-nerf: Neural radiance fields for street views. arXiv preprint arXiv:2303.00749 , 2023. 3, 7, 2 - · arXiv
  44. [47][47] Linning Xu, Yuanbo Xiangli, Sida Peng, Xingang Pan, Nanxuan Zhao, Christian Theobalt, Bo Dai, and Dahua Lin. Grid-guided neural radiance fields for large urban scenes. In CVPR , pages 8296-8306, 2023. 3 -
  45. [48][48] Qiangeng Xu, Zexiang Xu, Julien Philip, Sai Bi, Zhixin Shu, Kalyan Sunkavalli, and Ulrich Neumann. Point-nerf: Pointbased neural radiance fields. In CVPR , pages 5438-5448, 2022. 7, 4 -
  46. [49][49] Jiawei Yang, Boris Ivanovic, Or Litany, Xinshuo Weng, Seung Wook Kim, Boyi Li, Tong Che, Danfei Xu, Sanja Fidler, Marco Pavone, et al. Emernerf: Emergent spatial-temporal scene decomposition via self-supervision. arXiv preprint arXiv:2311.02077 , 2023. 1, 3, 6, 7, 2 - · arXiv
  47. [50][50] Ze Yang, Yun Chen, Jingkang Wang, Sivabalan Manivasagam, Wei-Chiu Ma, Anqi Joyce Yang, and Raquel Urtasun. Unisim: A neural closed-loop sensor simulator. In CVPR , pages 1389-1399, 2023. 3 -
  48. [51][51] 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. 2, 3 - · arXiv
  49. [52][52] MI Zhenxing and Dan Xu. Switch-nerf: Learning scene decomposition with mixture of experts for large-scale neural radiance fields. In ICLR , 2022. 2, 3 -
  50. [53][53] Xueyan Zou, Jianwei Yang, Hao Zhang, Feng Li, Linjie Li, Jianfeng Gao, and Yong Jae Lee. Segment everything everywhere all at once. arXiv preprint arXiv:2304.06718 , 2023. 2 · arXiv

Cited by

Sorted by citations

Authors
Zhou, X., Lin, Z., Shan, X., Wang, Y., Sun, D., & Yang, M.-H.
Affiliations
  • Peking University (CN)
  • Google (United States) (US)
ORCID
Venue
2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2024-06-16
Pages
21634-21643
ISSN
1063-6919 (ISSN-L)
DOI
10.1109/cvpr52733.2024.02044
OpenAlex
W4402754225
Cited by
248
References
4
Citations by year
2026: 98 · 2025: 117 · 2024: 33
FWCI
69.02
Type
conference paper
Language
en
Open access
Licence
Locations
  • IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Funders
National Key R&D Program of China (2022ZD0160305)
Topics
  • Physical Sciences › Engineering › Computational Mechanics › 3D Shape Modeling and Analysis
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Vision and Imaging
  • Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Computer Graphics and Visualization Techniques
Keywords
3D Gaussian Splatting, dynamic scene reconstruction, moving object reconstruction, occlusion handling, photorealistic rendering

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review