中文
相关论文

相关论文: Dynamics-Aware Gaussian Splatting Streaming Toward…

200 篇论文

Online reconstruction of dynamic scenes aims to learn from streaming multi-view inputs under low-latency constraints. The fast training and real-time rendering capabilities of 3D Gaussian Splatting have made on-the-fly reconstruction…

计算机视觉与模式识别 · 计算机科学 2026-03-27 Wonjoon Lee , Sungmin Woo , Donghyeong Kim , Jungho Lee , Sangheon Park , Sangyoun Lee

The advent of 3D Gaussian splatting (3DGS) has significantly enhanced the quality of volumetric video representation. Meanwhile, in contrast to conventional volumetric video, 3DGS video poses significant challenges for streaming due to its…

计算机视觉与模式识别 · 计算机科学 2025-07-22 Han Gong , Qiyue Li , Zhi Liu , Hao Zhou , Peng Yuan Zhou , Zhu Li , Jie Li

Recent advances in 3D Gaussian Splatting (3DGS) have enabled efficient free-viewpoint rendering and photorealistic scene reconstruction. While on-the-fly extensions of 3DGS have shown promise for real-time reconstruction from monocular RGB…

计算机视觉与模式识别 · 计算机科学 2025-12-10 Yijia Guo , Tong Hu , Zhiwei Li , Liwen Hu , Keming Qian , Xitong Lin , Shengbo Chen , Tiejun Huang , Lei Ma

3D Gaussian Splatting (3DGS) has garnered significant attention due to its superior scene representation fidelity and real-time rendering performance, especially for dynamic 3D scene reconstruction (\textit{i.e.}, 4D reconstruction).…

计算机视觉与模式识别 · 计算机科学 2025-10-14 Henan Wang , Hanxin Zhu , Xinliang Gong , Tianyu He , Xin Li , Zhibo Chen

3D Gaussian Splatting (3D-GS) is a recent 3D scene reconstruction technique that enables real-time rendering of novel views by modeling scenes as parametric point clouds of differentiable 3D Gaussians. However, its rendering speed and model…

计算机视觉与模式识别 · 计算机科学 2026-02-24 Alex Hanson , Allen Tu , Geng Lin , Vasu Singla , Matthias Zwicker , Tom Goldstein

4D Gaussian Splatting (4DGS) enables high-quality dynamic novel view synthesis, yet current models remain monolithic bitstreams that clients must download in full before any frame can be rendered, causing black-screen waits of tens to…

计算机视觉与模式识别 · 计算机科学 2026-05-13 Jiachen Li , Guangzhi Han , Jin Wan , Delong Han , Yuan Gao , Min Li , Mingle Zhou , Gang Li

Digitizing 3D static scenes and 4D dynamic events from multi-view images has long been a challenge in computer vision and graphics. Recently, 3D Gaussian Splatting (3DGS) has emerged as a practical and scalable reconstruction method,…

计算机视觉与模式识别 · 计算机科学 2024-09-18 Marko Mihajlovic , Sergey Prokudin , Siyu Tang , Robert Maier , Federica Bogo , Tony Tung , Edmond Boyer

Dynamic 3D scene representation and novel view synthesis are crucial for enabling immersive experiences required by AR/VR and metaverse applications. It is a challenging task due to the complexity of unconstrained real-world scenes and…

计算机视觉与模式识别 · 计算机科学 2025-08-07 Zeyu Yang , Zijie Pan , Xiatian Zhu , Li Zhang , Jianfeng Feng , Yu-Gang Jiang , Philip H. S. Torr

Reconstructing dynamic 3D scenes from 2D images and generating diverse views over time is challenging due to scene complexity and temporal dynamics. Despite advancements in neural implicit models, limitations persist: (i) Inadequate Scene…

计算机视觉与模式识别 · 计算机科学 2024-02-23 Zeyu Yang , Hongye Yang , Zijie Pan , Li Zhang

3D Gaussian Splatting (3DGS) enables high-quality rendering of 3D scenes and is getting increasing adoption in domains like autonomous driving and embodied intelligence. However, 3DGS still faces major efficiency challenges when faced with…

硬件体系结构 · 计算机科学 2025-07-31 Linye Wei , Jiajun Tang , Fan Fei , Boxin Shi , Runsheng Wang , Meng Li

Constructing photo-realistic Free-Viewpoint Videos (FVVs) of dynamic scenes from multi-view videos remains a challenging endeavor. Despite the remarkable advancements achieved by current neural rendering techniques, these methods generally…

计算机视觉与模式识别 · 计算机科学 2024-06-12 Jiakai Sun , Han Jiao , Guangyuan Li , Zhanjie Zhang , Lei Zhao , Wei Xing

Novel view synthesis has shown rapid progress recently, with methods capable of producing increasingly photorealistic results. 3D Gaussian Splatting has emerged as a promising method, producing high-quality renderings of scenes and enabling…

计算机视觉与模式识别 · 计算机科学 2024-07-19 Richard Shaw , Michal Nazarczuk , Jifei Song , Arthur Moreau , Sibi Catley-Chandar , Helisa Dhamo , Eduardo Perez-Pellitero

We propose StreamME, a method focuses on fast 3D avatar reconstruction. The StreamME synchronously records and reconstructs a head avatar from live video streams without any pre-cached data, enabling seamless integration of the…

图形学 · 计算机科学 2025-07-24 Luchuan Song , Yang Zhou , Zhan Xu , Yi Zhou , Deepali Aneja , Chenliang Xu

Recent significant advances in 3D scene representation have been driven by 3D Gaussian Splatting (3DGS), which has enabled real-time rendering with photorealistic quality. 3DGS often requires a large number of primitives to achieve high…

计算机视觉与模式识别 · 计算机科学 2026-03-02 Haoran Wang , Guoxi Huang , Fan Zhang , David Bull , Nantheera Anantrasirichai

3D Gaussian Splatting (GS) has emerged as a powerful representation for high-quality scene reconstruction, offering compelling rendering quality. However, the training process of GS often suffers from slow convergence due to inefficient…

计算机视觉与模式识别 · 计算机科学 2025-07-29 Binxiao Huang , Zhengwu Liu , Ngai Wong

3D Gaussian Splatting achieves high-fidelity novel view synthesis, but its application to online long-sequence scenarios is still limited. Existing methods either rely on slow per-scene optimization or fail to provide efficient incremental…

计算机视觉与模式识别 · 计算机科学 2025-07-23 Guichen Huang , Ruoyu Wang , Xiangjun Gao , Che Sun , Yuwei Wu , Shenghua Gao , Yunde Jia

The accurate reconstruction of dynamic street scenes is critical for applications in autonomous driving, augmented reality, and virtual reality. Traditional methods relying on dense point clouds and triangular meshes struggle with moving…

计算机视觉与模式识别 · 计算机科学 2026-05-05 Peizhen Zheng , Dongjing Jiang , Qingchong Jiao , Redouane EL Bouchtaoui , Flynnwell Jianfei Zhang

Dynamic 3D scene reconstruction is essential for immersive media such as VR, MR, and XR, yet remains challenging for long multi-view sequences with large-scale motion. Existing dynamic Gaussian approaches are either Frame-Stream, offering…

计算机视觉与模式识别 · 计算机科学 2026-04-16 Jie Liang , Jiahao Wu , Chao Wang , Jiayu Yang , Xiaoyun Zheng , Kaiqiang Xiong , Zhanke Wang , Jinbo Yan , Feng Gao , Ronggang Wang

Modeling complex rigid motion across large spatiotemporal spans remains an unresolved challenge in dynamic reconstruction. Existing paradigms are mainly confined to short-term, small-scale deformation and offer limited consideration for…

计算机视觉与模式识别 · 计算机科学 2026-01-06 Yijun Xu , Jingrui Zhang , Yuhan Chen , Dingwen Wang , Lei Yu , Chu He

This paper addresses the problem of dynamic scene surface reconstruction using Gaussian Splatting (GS), aiming to recover temporally consistent geometry. While existing GS-based dynamic surface reconstruction methods can yield superior…

计算机视觉与模式识别 · 计算机科学 2026-03-31 Renjie Wu , Hongdong Li , Jose M. Alvarez , Miaomiao Liu