Fov-GS: Foveated 3D Gaussian Splatting for Dynamic Scenes
Runze Fan, Jian Wu, Xuehuai Shi, Lizhi Zhao, Qixiang Ma, Lili Wang
Abstract
Rendering quality and performance greatly affect the user's immersion in VR experiences. 3D Gaussian Splatting-based methods can achieve photo-realistic rendering with speeds of over 100 fps in static scenes, but the speed drops below 10 fps in monocular dynamic scenes. Foveated rendering provides a possible solution to accelerate rendering without compromising visual perceptual quality. However, 3DGS and foveated rendering are not compatible. In this paper, we propose Fov-GS, a foveated 3D Gaussian splatting method for rendering dynamic scenes in real time. We introduce a 3D Gaussian forest representation that represents the scene as a forest. To construct the 3D Gaussian forest, we propose a 3D Gaussian forest initialization method based on dynamic-static separation. Subsequently, we propose a 3D Gaussian forest optimization method based on deformation field and Gaussian decomposition to optimize the forest and deformation field. To achieve real-time dynamic scene rendering, we present a 3D Gaussian forest rendering method based on HVS models. Experiments demonstrate that our method not only achieves higher rendering quality in the foveal and salient regions compared to the SOTA methods but also dramatically improves rendering performance, achieving up to 11.33X speedup. We also conducted a user study, and the results prove that the perceptual quality of our method has a high visual similarity with the ground truth.
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.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 4ea21a6f-e04b-4668-a8be-4d346d22679aCited by top-tier papers4
- TreeSplat: Mergeable Tree for Deformable Gaussian SplattingQiuhong Shen, Xingyi Yang, Xinchao WangNeurIPS 2025 · 1 citation
- Motion Hierarchical Gaussian for Dynamic Control in VRRunze Fan, Jian Wu, Qixiang Ma, Zhikai Wen et al.IEEE VR 2026
- Illumination-Consistent Human-Scene Reconstruction from Monocular VideoRongbin Zheng, Wensheng Li, Lingzhe Zeng, Dong Wang et al.CVPR 2026
- CoRoGS: Contextual Gaussian Splatting for Robust Large-Deviation View SynthesisXin Ma, Peng Lu, Yisong Chen, Chengwei Pan et al.CVPR 2026
Builds on17
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 5,687 citations
- 4D Gaussian Splatting for Real-Time Dynamic Scene RenderingGuanjun Wu, Taoran Yi, Jiemin Fang, Lingxi Xie et al.CVPR 2024 · 513 citations
- Mip-Splatting: Alias-Free 3D Gaussian SplattingZehao Yu, Anpei Chen, Binbin Huang, Torsten Sattler et al.CVPR 2024 · 360 citations
- Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene ReconstructionZiyi Yang, Xinyu Gao, Wen Zhou, Shaohui Jiao et al.CVPR 2024 · 302 citations
- Tracking Anything with Decoupled Video SegmentationHo Kei Cheng, Seoung Wug Oh, Brian L. Price, Alexander G. Schwing et al.ICCV 2023 · 240 citations
Related papers
- Object-Space Analysis of Local Contrast Sensitivity for Hierarchical Representations of 3D GaussiansNaoto Yoshii, Suguru Saito, Masataka Sawayama, Yoshinori DobashiSIGGRAPH 2026
- 4D Gaussian Splatting with Scale-aware Residual Field and Adaptive Optimization for Real-time Rendering of Temporally Complex Dynamic ScenesJinbo Yan, Rui Peng, Luyang Tang, Ronggang WangACM MM 2024 · 23 citations
- Hybrid Foveated Path Tracing with Peripheral Gaussians for Immersive AnatomyConstantin Kleinbeck, Luisa Theelke, Hannah Schieber, Ulrich Eck et al.IEEE VR 2026
- EdgeGaussian: Real-time Free-Viewpoint Video for Mobile VR via Edge-Client Collaborative Neural RenderingZhihui Ke, Xiaobo Zhou, Yuyang Liu, Zhizhuo Pang et al.MobiCom 2025 · 1 citation
- SHARP-GS: Scalable High-fidelity Accelerated Rendering Pipeline for Ultra-high Resolution 3D Gaussian SplattingJunran Ding, Weihang Liu, Yuke Li, Yizhou Wang et al.SIGGRAPH 2026
