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

计算机科学 计算机图形学(图像) 计算机视觉 人工智能 高斯分布 物理 量子力学
作者
Runze Fan,Jian Wu,Xuehuai Shi,Lizhi Zhao,Qixiang Ma,Lili Wang
出处
期刊:IEEE Transactions on Visualization and Computer Graphics [Institute of Electrical and Electronics Engineers]
卷期号:: 1-11 被引量:3
标识
DOI:10.1109/tvcg.2025.3549576
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 11.33× 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.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
星辰大海的应助被joinn采纳,获得10
1秒前
2秒前
卿佑发布了新的文献求助10
2秒前
绷不住完成签到,获得积分10
3秒前
bian完成签到,获得积分10
4秒前
M先生发布了新的文献求助10
5秒前
CipherSage的应助被欣欣采纳,获得10
5秒前
仇剑封完成签到,获得积分10
5秒前
hadal完成签到,获得积分10
6秒前
安逸1发布了新的文献求助10
9秒前
10秒前
orixero的应助被吃的采纳,获得10
12秒前
13秒前
14秒前
郝子凯的应助被科研通管家采纳,获得30
14秒前
领导范儿的应助被科研通管家采纳,获得10
14秒前
搜集达人的应助被科研通管家采纳,获得10
15秒前
丘比特的应助被科研通管家采纳,获得10
15秒前
苹果沛蓝发布了新的文献求助10
15秒前
wanci的应助被科研通管家采纳,获得30
15秒前
molihuakai的应助被科研通管家采纳,获得10
15秒前
DW的应助被科研通管家采纳,获得10
15秒前
脑洞疼的应助被科研通管家采纳,获得10
15秒前
毗昙的应助被科研通管家采纳,获得10
15秒前
DW的应助被科研通管家采纳,获得10
16秒前
16秒前
英姑的应助被科研通管家采纳,获得10
16秒前
充电宝的应助被科研通管家采纳,获得10
16秒前
Hello的应助被科研通管家采纳,获得10
16秒前
卿佑完成签到,获得积分10
16秒前
打打的应助被科研通管家采纳,获得10
16秒前
彭于晏的应助被科研通管家采纳,获得10
16秒前
欣慰碧彤的应助被科研通管家采纳,获得10
16秒前
充电宝的应助被科研通管家采纳,获得10
16秒前
17秒前
大个的应助被科研通管家采纳,获得10
17秒前
欣欣发布了新的文献求助10
17秒前
渡人舟的应助被科研通管家采纳,获得10
17秒前
爆米花的应助被科研通管家采纳,获得10
17秒前
wbx完成签到,获得积分10
17秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
自動車の空力技術 800
Essentials of Carbohydrate Chemistry and Biochemistry, 4th Edition 800
Organizational Behavior 510
Management and the Arts 510
Matrix Methods in Data Mining and Pattern Recognition Second Edition 510
Issues in Task-Based Language Teaching 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 化学工程 工程类 有机化学 物理 复合材料 生物化学 内科学 细胞生物学 基因 遗传学 免疫学 冶金 光电子学 癌症研究
热门帖子
关注 科研通微信公众号,转发送积分 7784005
求助须知:如何正确求助?哪些是违规求助? 9323314
关于积分的说明 20393938
捐赠科研通 7372688
什么是DOI,文献DOI怎么找? 3320878
关于科研通互助平台的介绍 2468807
邀请新用户注册赠送积分活动 2337088