Fov-GS: Foveated 3D Gaussian Splatting for Dynamic Scenes
Runze Fan, Jian Wu, Xuehuai Shi, Lizhi Zhao, Qixiang Ma, Lili Wang
摘要
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.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了最后一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper4
- TreeSplat: Mergeable Tree for Deformable Gaussian SplattingQiuhong Shen, Xingyi Yang, Xinchao WangNeurIPS 2025 · 被引用 1 次
- Motion Hierarchical Gaussian for Dynamic Control in VRRunze Fan, Jian Wu, Qixiang Ma, Zhikai Wen 等IEEE VR 2026
- Illumination-Consistent Human-Scene Reconstruction from Monocular VideoRongbin Zheng, Wensheng Li, Lingzhe Zeng, Dong Wang 等CVPR 2026
- CoRoGS: Contextual Gaussian Splatting for Robust Large-Deviation View SynthesisXin Ma, Peng Lu, Yisong Chen, Chengwei Pan 等CVPR 2026
它引用的顶会 Paper17
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 被引用 5,687 次
- 4D Gaussian Splatting for Real-Time Dynamic Scene RenderingGuanjun Wu, Taoran Yi, Jiemin Fang, Lingxi Xie 等CVPR 2024 · 被引用 513 次
- Mip-Splatting: Alias-Free 3D Gaussian SplattingZehao Yu, Anpei Chen, Binbin Huang, Torsten Sattler 等CVPR 2024 · 被引用 360 次
- Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene ReconstructionZiyi Yang, Xinyu Gao, Wen Zhou, Shaohui Jiao 等CVPR 2024 · 被引用 302 次
- Tracking Anything with Decoupled Video SegmentationHo Kei Cheng, Seoung Wug Oh, Brian L. Price, Alexander G. Schwing 等ICCV 2023 · 被引用 240 次
相关 Paper
- 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 · 被引用 23 次
- Hybrid Foveated Path Tracing with Peripheral Gaussians for Immersive AnatomyConstantin Kleinbeck, Luisa Theelke, Hannah Schieber, Ulrich Eck 等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 等MobiCom 2025 · 被引用 1 次
- SHARP-GS: Scalable High-fidelity Accelerated Rendering Pipeline for Ultra-high Resolution 3D Gaussian SplattingJunran Ding, Weihang Liu, Yuke Li, Yizhou Wang 等SIGGRAPH 2026
