• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

Fov-GS: Foveated 3D Gaussian Splatting for Dynamic Scenes.

作者信息

Fan Runze, Wu Jian, Shi Xuehuai, Zhao Lizhi, Ma Qixiang, Wang Lili

出版信息

IEEE Trans Vis Comput Graph. 2025 May;31(5):2975-2985. doi: 10.1109/TVCG.2025.3549576. Epub 2025 Apr 25.

DOI:10.1109/TVCG.2025.3549576
PMID:40100683
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.

摘要

相似文献

1
Fov-GS: Foveated 3D Gaussian Splatting for Dynamic Scenes.
IEEE Trans Vis Comput Graph. 2025 May;31(5):2975-2985. doi: 10.1109/TVCG.2025.3549576. Epub 2025 Apr 25.
2
MPGS: Multi-Plane Gaussian Splatting for Compact Scenes Rendering.MPGS:用于紧凑场景渲染的多平面高斯点渲染
IEEE Trans Vis Comput Graph. 2025 May;31(5):3256-3266. doi: 10.1109/TVCG.2025.3549551. Epub 2025 Apr 25.
3
Scene-Aware Foveated Neural Radiance Fields.场景感知的中央凹神经辐射场
IEEE Trans Vis Comput Graph. 2025 Sep;31(9):5039-5054. doi: 10.1109/TVCG.2024.3429416.
4
Audio-visual aware Foveated Rendering.视听感知的中央凹渲染。
IEEE Trans Vis Comput Graph. 2025 Mar 26;PP. doi: 10.1109/TVCG.2025.3554737.
5
PGSR: Planar-Based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction.PGSR:基于平面的高斯点云绘制,用于高效且高保真的曲面重建。
IEEE Trans Vis Comput Graph. 2025 Sep;31(9):6100-6111. doi: 10.1109/TVCG.2024.3494046.
6
Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussians.八叉树高斯曲面法:迈向基于层次细节结构三维高斯曲面的一致实时渲染
IEEE Trans Pattern Anal Mach Intell. 2025 May 8;PP. doi: 10.1109/TPAMI.2025.3568201.
7
iVR-GS: Inverse Volume Rendering for Explorable Visualization via Editable 3D Gaussian Splatting.iVR-GS:通过可编辑的3D高斯点渲染实现可探索可视化的逆体积渲染
IEEE Trans Vis Comput Graph. 2025 Jun;31(6):3783-3795. doi: 10.1109/TVCG.2025.3567121.
8
VPRF: Visual Perceptual Radiance Fields for Foveated Image Synthesis.VPRF:用于中央凹图像合成的视觉感知辐射场
IEEE Trans Vis Comput Graph. 2024 Nov;30(11):7183-7192. doi: 10.1109/TVCG.2024.3456184. Epub 2024 Oct 10.
9
Frequency-Aware Uncertainty Gaussian Splatting for Dynamic Scene Reconstruction.
IEEE Trans Vis Comput Graph. 2025 May;31(5):3558-3568. doi: 10.1109/TVCG.2025.3549143. Epub 2025 Apr 25.
10
Look at the Sky: Sky-Aware Efficient 3D Gaussian Splatting in the Wild.
IEEE Trans Vis Comput Graph. 2025 May;31(5):3481-3491. doi: 10.1109/TVCG.2025.3549187. Epub 2025 Apr 25.