中文
相关论文

相关论文: Gaussian Sequences with Multi-Scale Dynamics for 4…

200 篇论文

Dynamic urban scene modeling is a rapidly evolving area with broad applications. While current approaches leveraging neural radiance fields or Gaussian Splatting have achieved fine-grained reconstruction and high-fidelity novel view…

计算机视觉与模式识别 · 计算机科学 2026-05-11 Yuru Xiao , Zihan Lin , Chao Lu , Deming Zhai , Kui Jiang , Wenbo Zhao , Wei Zhang , Junjun Jiang , Huanran Wang , Xianming Liu

Visual understanding of the world goes beyond the semantics and flat structure of individual images. In this work, we aim to capture both the 3D structure and dynamics of real-world scenes from monocular real-world videos. Our Dynamic Scene…

计算机视觉与模式识别 · 计算机科学 2024-03-18 Maximilian Seitzer , Sjoerd van Steenkiste , Thomas Kipf , Klaus Greff , Mehdi S. M. Sajjadi

Capturing general deforming scenes from monocular RGB video is crucial for many computer graphics and vision applications. However, current approaches suffer from drawbacks such as struggling with large scene deformations, inaccurate shape…

计算机视觉与模式识别 · 计算机科学 2023-05-05 Erik C. M. Johnson , Marc Habermann , Soshi Shimada , Vladislav Golyanik , Christian Theobalt

3D Gaussian Splatting (3DGS) has become an emerging tool for dynamic scene reconstruction. However, existing methods focus mainly on extending static 3DGS into a time-variant representation, while overlooking the rich motion information…

计算机视觉与模式识别 · 计算机科学 2024-03-19 Zhiyang Guo , Wengang Zhou , Li Li , Min Wang , Houqiang Li

Dynamic scene rendering opens new avenues in autonomous driving by enabling closed-loop simulations with photorealistic data, which is crucial for validating end-to-end algorithms. However, the complex and highly dynamic nature of traffic…

计算机视觉与模式识别 · 计算机科学 2025-03-11 Rui Song , Chenwei Liang , Yan Xia , Walter Zimmer , Hu Cao , Holger Caesar , Andreas Festag , Alois Knoll

Instant reconstruction of dynamic 3D humans from uncalibrated sparse-view videos is critical for numerous downstream applications. Existing methods, however, are either limited by the slow reconstruction speeds or incapable of generating…

计算机视觉与模式识别 · 计算机科学 2025-09-30 Yingdong Hu , Yisheng He , Jinnan Chen , Weihao Yuan , Kejie Qiu , Zehong Lin , Siyu Zhu , Zilong Dong , Jun Zhang

Achieving truly practical dynamic 3D reconstruction requires online operation, global pose and map consistency, detailed appearance modeling, and the flexibility to handle both RGB and RGB-D inputs. However, existing SLAM methods typically…

计算机视觉与模式识别 · 计算机科学 2025-09-23 Shi Chen , Erik Sandström , Sandro Lombardi , Siyuan Li , Martin R. Oswald

Animatable 3D reconstruction has significant applications across various fields, primarily relying on artists' handcraft creation. Recently, some studies have successfully constructed animatable 3D models from monocular videos. However,…

计算机视觉与模式识别 · 计算机科学 2024-03-19 Tingyang Zhang , Qingzhe Gao , Weiyu Li , Libin Liu , Baoquan Chen

This paper addresses the problem of decomposed 4D scene reconstruction from multi-view videos. Recent methods achieve this by lifting video segmentation results to a 4D representation through differentiable rendering techniques. Therefore,…

计算机视觉与模式识别 · 计算机科学 2025-12-30 Yongzhen Hu , Yihui Yang , Haotong Lin , Yifan Wang , Junting Dong , Yifu Deng , Xinyu Zhu , Fan Jia , Hujun Bao , Xiaowei Zhou , Sida Peng

Volumetric video is emerging as a key medium for digitizing the dynamic physical world, creating the virtual environments with six degrees of freedom to deliver immersive user experiences. However, robustly modeling general dynamic scenes,…

The reconstruction of three-dimensional dynamic scenes is a well-established yet challenging task within the domain of computer vision. In this paper, we propose a novel approach that combines the domains of 3D geometry reconstruction and…

计算机视觉与模式识别 · 计算机科学 2025-09-11 David Stotko , Reinhard Klein

Photorealistic 3D reconstruction of street scenes is a critical technique for developing real-world simulators for autonomous driving. Despite the efficacy of Neural Radiance Fields (NeRF) for driving scenes, 3D Gaussian Splatting (3DGS)…

计算机视觉与模式识别 · 计算机科学 2024-05-31 Nan Huang , Xiaobao Wei , Wenzhao Zheng , Pengju An , Ming Lu , Wei Zhan , Masayoshi Tomizuka , Kurt Keutzer , Shanghang Zhang

Accurate reconstruction of complex dynamic scenes from just a single viewpoint continues to be a challenging task in computer vision. Current dynamic novel view synthesis methods typically require videos from many different camera…

计算机视觉与模式识别 · 计算机科学 2024-07-08 Basile Van Hoorick , Rundi Wu , Ege Ozguroglu , Kyle Sargent , Ruoshi Liu , Pavel Tokmakov , Achal Dave , Changxi Zheng , Carl Vondrick

Novel view synthesis of dynamic scenes is fundamental to achieving photorealistic 4D reconstruction and immersive visual experiences. Recent progress in Gaussian-based representations has significantly improved real-time rendering quality,…

计算机视觉与模式识别 · 计算机科学 2026-02-06 Zhanfeng Liao , Jiajun Zhang , Hanzhang Tu , Zhixi Wang , Yunqi Gao , Hongwen Zhang , Yebin Liu

The ability to extrapolate dynamic 3D scenes beyond the observed timeframe is fundamental to advancing physical world understanding and predictive modeling. Existing dynamic 3D reconstruction methods have achieved high-fidelity rendering of…

计算机视觉与模式识别 · 计算机科学 2025-12-01 Jinsheng Quan , Qiaowei Miao , Yichao Xu , Zizhuo Lin , Ying Li , Wei Yang , Zhihui Li , Yawei Luo

The development of generalizable Novel View Synthesis (NVS) models is critically limited by the scarcity of large-scale training data featuring diverse and precise camera trajectories. While real-world captures are photorealistic, they are…

计算机视觉与模式识别 · 计算机科学 2026-04-14 Chenhan Jiang , Yu Chen , Qingwen Zhang , Jifei Song , Songcen Xu , Dit-Yan Yeung , Jiankang Deng

We present Orientation-anchored Gaussian Splatting (OriGS), a novel framework for high-quality 4D reconstruction from casually captured monocular videos. While recent advances extend 3D Gaussian Splatting to dynamic scenes via various…

计算机视觉与模式识别 · 计算机科学 2025-09-30 Junyi Wu , Jiachen Tao , Haoxuan Wang , Gaowen Liu , Ramana Rao Kompella , Yan Yan

Existing NeRF-based methods for large scene reconstruction often have limitations in visual quality and rendering speed. While the recent 3D Gaussian Splatting works well on small-scale and object-centric scenes, scaling it up to large…

计算机视觉与模式识别 · 计算机科学 2024-02-28 Jiaqi Lin , Zhihao Li , Xiao Tang , Jianzhuang Liu , Shiyong Liu , Jiayue Liu , Yangdi Lu , Xiaofei Wu , Songcen Xu , Youliang Yan , Wenming Yang

In real-world scenarios, environment changes caused by human or agent activities make it extremely challenging for robots to perform various long-term tasks. Recent works typically struggle to effectively understand and adapt to dynamic…

机器人学 · 计算机科学 2025-12-19 Luzhou Ge , Xiangyu Zhu , Zhuo Yang , Xuesong Li

While dynamic novel view synthesis from 2D videos has seen progress, achieving efficient reconstruction and rendering of dynamic scenes remains a challenging task. In this paper, we introduce Disentangled 4D Gaussian Splatting…

图形学 · 计算机科学 2025-10-31 Hao Feng , Hao Sun , Wei Xie , Zhi Zuo , Zhengzhe Liu