Fov-GS:动态场景的注视点3D高斯飞溅。

Runze Fan;Jian Wu;Xuehuai Shi;Lizhi Zhao;Qixiang Ma;Lili Wang
{"title":"Fov-GS:动态场景的注视点3D高斯飞溅。","authors":"Runze Fan;Jian Wu;Xuehuai Shi;Lizhi Zhao;Qixiang Ma;Lili Wang","doi":"10.1109/TVCG.2025.3549576","DOIUrl":null,"url":null,"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.","PeriodicalId":94035,"journal":{"name":"IEEE transactions on visualization and computer graphics","volume":"31 5","pages":"2975-2985"},"PeriodicalIF":0.0000,"publicationDate":"2025-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Fov-GS: Foveated 3D Gaussian Splatting for Dynamic Scenes\",\"authors\":\"Runze Fan;Jian Wu;Xuehuai Shi;Lizhi Zhao;Qixiang Ma;Lili Wang\",\"doi\":\"10.1109/TVCG.2025.3549576\",\"DOIUrl\":null,\"url\":null,\"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.\",\"PeriodicalId\":94035,\"journal\":{\"name\":\"IEEE transactions on visualization and computer graphics\",\"volume\":\"31 5\",\"pages\":\"2975-2985\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2025-03-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE transactions on visualization and computer graphics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://ieeexplore.ieee.org/document/10932755/\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE transactions on visualization and computer graphics","FirstCategoryId":"1085","ListUrlMain":"https://ieeexplore.ieee.org/document/10932755/","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

渲染质量和性能极大地影响了用户在VR体验中的沉浸感。基于三维高斯喷溅的方法可以在静态场景中实现100 fps以上的逼真渲染,但在单目动态场景中速度下降到10 fps以下。注视点渲染提供了一种可能的解决方案,可以在不影响视觉感知质量的情况下加速渲染。然而,3DGS和注视点渲染不兼容。在本文中,我们提出了Fov-GS,一种用于实时渲染动态场景的注视点三维高斯飞溅方法。我们引入了一个3D高斯森林表示,将场景表示为森林。为了构造三维高斯森林,提出了一种基于动静分离的三维高斯森林初始化方法。随后,我们提出了一种基于变形场和高斯分解的三维高斯森林优化方法,对森林和变形场进行优化。为了实现实时动态场景渲染,提出了一种基于HVS模型的三维高斯森林渲染方法。实验表明,与SOTA方法相比,我们的方法不仅在中央凹区和显著区获得了更高的渲染质量,而且显著提高了渲染性能,实现了高达11.33倍的加速。我们还进行了用户研究,结果证明我们方法的感知质量与地面真实具有很高的视觉相似性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Fov-GS: Foveated 3D Gaussian Splatting for Dynamic Scenes
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.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信