SeG-Gaussian:Segmentation-Guided 3D Gaussian Optimization for Novel View Synthesis
文献类型：期刊论文
| 作者 | Zhang, Ling-Xiao2,3; Jiang, Chenbo1; Lai, Yu-Kun4; Gao, Lin2,3 |
| 刊名 | IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
 |
| 出版日期 | 2025-12-01 |
| 卷号 | 31期号:12页码:10815-10827 |
| 关键词 | Three-dimensional displays Rendering (computer graphics) Neural radiance field Cloning Real-time systems Training Geometry Optimization Graphical models Distribution functions Gaussian splatting radiance fields semantic guidance regularization |
| ISSN号 | 1077-2626 |
| DOI | 10.1109/TVCG.2025.3615421 |
| 英文摘要 | Radiance field based methods have recently revolutionized novel view synthesis of scenes captured with multi-view photos. A significant recent advance is 3D Gaussian Splatting (3DGS), which utilizes a set of 3D Gaussians to represent a radiance field, yielding high-fidelity results in real-time rendering. However, we have observed that 3DGS struggles to capture the necessary details in sparsely observed regions, where there is not enough gradient for effective split and clone operations. In this paper, we present a novel solution to address this limitation. Our key idea is to leverage segmentation information to identify poorly optimized regions within the 3D Gaussian representation. By applying split or clone operations on the corresponding 3D Gaussians in these regions, we aim to refine the spatial distribution of Gaussians and enhance the overall quality of high-fidelity 3D scene reconstruction. To further optimize the reconstruction process, we introduce two spatial regularization terms: repulsion loss and smoothness loss. These terms effectively minimize overlap and redundancy among Gaussians, reducing outliers in the synthesized geometry. By incorporating these regularization techniques, our approach achieves state-of-the-art performance in real-time novel view synthesis and significantly improves visibility in less observed regions, leading to a more compact and accurate 3D scene representation. |
| 资助项目 | National Natural Science Foundation of China[62322210] ; Beijing Municipal Science and Technology Commission[Z231100005923031] ; Innovation Funding of ICT, CAS[E461020] |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:001611559200016 |
| 出版者 | IEEE COMPUTER SOC |
| 源URL | [http://119.78.100.204/handle/2XEOYT63/43101]  |
| 专题 | 中国科学院计算技术研究所 |
| 通讯作者 | Gao, Lin |
| 作者单位 | 1.McGill Univ, Montreal, PQ H3A 0G4, Canada 2.Chinese Acad Sci, Beijing Key Lab Mobile Comp & Pervas Device, Inst Comp Technol, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Beijing 101408, Peoples R China 4.Cardiff Univ, Sch Comp Sci & Informat, Cardiff CF24 4AG, Wales |
| 推荐引用方式 GB/T 7714 | Zhang, Ling-Xiao,Jiang, Chenbo,Lai, Yu-Kun,et al. SeG-Gaussian:Segmentation-Guided 3D Gaussian Optimization for Novel View Synthesis[J]. IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS,2025,31(12):10815-10827. |
| APA | Zhang, Ling-Xiao,Jiang, Chenbo,Lai, Yu-Kun,&Gao, Lin.(2025).SeG-Gaussian:Segmentation-Guided 3D Gaussian Optimization for Novel View Synthesis.IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS,31(12),10815-10827. |
| MLA | Zhang, Ling-Xiao,et al."SeG-Gaussian:Segmentation-Guided 3D Gaussian Optimization for Novel View Synthesis".IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS 31.12(2025):10815-10827. |
入库方式： OAI收割
来源：计算技术研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。