Hierarchy UGP: Hierarchy Unified Gaussian Primitive for Large-Scale Dynamic Scene Reconstruction
Hongyang Sun, Qinglin Yang, Jiawei Wang, Zhen Xu, Chen Liu, Yida Wang, Kun Zhan, Hujun Bao, Xiaowei Zhou, Sida Peng
2025Year
Abstract
3 UESTC Figure 1. Overview of the Reconstruction Improvement of Our Hierarchy UGP on Large-Scale and Large-Motion Scenarios. On the large-scale dynamic scene, the reconstruction quality of Hierarchy UGP significantly outperforms previous methods [4, 40]. For reconstruction of pedestrian with large motions, Hierarchy UGP also demonstrates large improvements.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Builds on24
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 5,687 citations
- Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance FieldsJonathan T. Barron, Ben Mildenhall, Dor Verbin, Pratul P. Srinivasan et al.CVPR 2022 · 1,603 citations
- Plenoxels: Radiance Fields without Neural NetworksSara Fridovich-Keil, Alex Yu, Matthew Tancik, Qinhong Chen et al.CVPR 2022 · 1,237 citations
- Block-NeRF: Scalable Large Scene Neural View SynthesisMatthew Tancik, Vincent Casser, Xinchen Yan, Sabeek Pradhan et al.CVPR 2022 · 702 citations
- Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian SplattingZeyu Yang, Hongye Yang, Zijie Pan, Li ZhangICLR 2024 · 529 citations
Related papers
- VisFusion: Visibility-Aware Online 3D Scene Reconstruction from VideosHuiyu Gao, Wei Mao, Miaomiao LiuCVPR 2023
- Generative Densification: Learning to Densify Gaussians for High-Fidelity Generalizable 3D ReconstructionSeungtae Nam, Xiangyu Sun, Gyeongjin Kang, Younggeun Lee et al.CVPR 2025
- GP-NeRF: Generalized Perception NeRF for Context-Aware 3D Scene UnderstandingHao Li, Dingwen Zhang, Yalun Dai, Nian Liu et al.CVPR 2024
- FreeTimeGS: Free Gaussian Primitives at Anytime Anywhere for Dynamic Scene ReconstructionYifan Wang, Peishan Yang, Zhen Xu, Jiaming Sun et al.CVPR 2025
- Unifying Short and Long-Term Tracking with Graph HierarchiesOrcun Cetintas, Guillem Brasó, Laura Leal-TaixéCVPR 2023
