中文
相关论文

相关论文: Self-Calibrating 4D Novel View Synthesis from Mono…

200 篇论文

Recently, 3D Gaussian Splatting (3DGS) has exceled in novel view synthesis (NVS) with its real-time rendering capabilities and superior quality. However, it faces challenges for high-resolution novel view synthesis (HRNVS) due to the coarse…

计算机视觉与模式识别 · 计算机科学 2024-12-12 Shiyun Xie , Zhiru Wang , Xu Wang , Yinghao Zhu , Chengwei Pan , Xiwang Dong

Recent 4D reconstruction methods have yielded impressive results but rely on sharp videos as supervision. However, motion blur often occurs in videos due to camera shake and object movement, while existing methods render blurry results when…

计算机视觉与模式识别 · 计算机科学 2026-01-21 Renlong Wu , Zhilu Zhang , Mingyang Chen , Zifei Yan , Wangmeng Zuo

Conventional geometry-based SLAM systems lack dense 3D reconstruction capabilities since their data association usually relies on feature correspondences. Additionally, learning-based SLAM systems often fall short in terms of real-time…

计算机视觉与模式识别 · 计算机科学 2024-08-22 Zhongche Qu , Zhi Zhang , Cong Liu , Jianhua Yin

Recently, 3D Gaussian Splatting (3DGS) has emerged as an efficient approach for accurately representing scenes. However, despite its superior novel view synthesis capabilities, extracting the geometry of the scene directly from the Gaussian…

计算机视觉与模式识别 · 计算机科学 2024-07-18 Yaniv Wolf , Amit Bracha , Ron Kimmel

Scene view synthesis, which generates novel views from limited perspectives, is increasingly vital for applications like virtual reality, augmented reality, and robotics. Unlike object-based tasks, such as generating 360{\deg} views of a…

计算机视觉与模式识别 · 计算机科学 2025-04-29 Xiaofeng Jin , Yan Fang , Matteo Frosi , Jianfei Ge , Jiangjian Xiao , Matteo Matteucci

Persistent dynamic scene modeling for tracking and novel-view synthesis remains challenging due to the difficulty of capturing accurate deformations while maintaining computational efficiency. We propose SCas4D, a cascaded optimization…

计算机视觉与模式识别 · 计算机科学 2025-10-09 Jipeng Lyu , Jiahua Dong , Yu-Xiong Wang

Dynamic 4D Gaussian Splatting (4DGS) effectively extends the high-speed rendering capabilities of 3D Gaussian Splatting (3DGS) to represent volumetric videos. However, the large number of Gaussians, substantial temporal redundancies, and…

图形学 · 计算机科学 2026-01-14 Hyeongmin Lee , Kyungjune Baek

We introduce a novel method for dynamic free-view synthesis of an ambient scenes from a monocular capture bringing a immersive quality to the viewing experience. Our method builds upon the recent advancements in 3D Gaussian Splatting (3DGS)…

计算机视觉与模式识别 · 计算机科学 2024-06-14 Meng-Li Shih , Jia-Bin Huang , Changil Kim , Rajvi Shah , Johannes Kopf , Chen Gao

Recent neural rendering and reconstruction techniques, such as NeRFs or Gaussian Splatting, have shown remarkable novel view synthesis capabilities but require hundreds of images of the scene from diverse viewpoints to render high-quality…

计算机视觉与模式识别 · 计算机科学 2024-08-29 Felix Tristram , Stefano Gasperini , Nassir Navab , Federico Tombari

Generating synthetic images is a useful method for cheaply obtaining labeled data for training computer vision models. However, obtaining accurate 3D models of relevant objects is necessary, and the resulting images often have a gap in…

计算机视觉与模式识别 · 计算机科学 2025-04-14 Bram Vanherle , Brent Zoomers , Jeroen Put , Frank Van Reeth , Nick Michiels

We propose HoliGS, a novel deformable Gaussian splatting framework that addresses embodied view synthesis from long monocular RGB videos. Unlike prior 4D Gaussian splatting and dynamic NeRF pipelines, which struggle with training overhead…

计算机视觉与模式识别 · 计算机科学 2025-06-25 Xiaoyuan Wang , Yizhou Zhao , Botao Ye , Xiaojun Shan , Weijie Lyu , Lu Qi , Kelvin C. K. Chan , Yinxiao Li , Ming-Hsuan Yang

We present an efficient neural 3D scene representation for novel-view synthesis (NVS) in large-scale, dynamic urban areas. Existing works are not well suited for applications like mixed-reality or closed-loop simulation due to their limited…

计算机视觉与模式识别 · 计算机科学 2024-11-26 Tobias Fischer , Jonas Kulhanek , Samuel Rota Bulò , Lorenzo Porzi , Marc Pollefeys , Peter Kontschieder

3D Gaussian Splatting (3DGS) has demonstrated impressive performance in synthesizing novel views after training on a given set of viewpoints. However, its rendering quality deteriorates when the synthesized view deviates significantly from…

计算机视觉与模式识别 · 计算机科学 2025-03-13 Jiatong Xia , Lingqiao Liu

Scene reconstruction and novel-view synthesis for large, complex, multi-story, indoor scenes is a challenging and time-consuming task. Prior methods have utilized drones for data capture and radiance fields for scene reconstruction, both of…

计算机视觉与模式识别 · 计算机科学 2024-10-16 Yuanbo Chen , Chengyu Zhang , Jason Wang , Xuefan Gao , Avideh Zakhor

Text-driven 3D scene editing has attracted considerable interest due to its convenience and user-friendliness. However, methods that rely on implicit 3D representations, such as Neural Radiance Fields (NeRF), while effective in rendering…

计算机视觉与模式识别 · 计算机科学 2026-03-31 Pengcheng Xue , Yan Tian , Qiutao Song , Ziyi Wang , Linyang He , Weiping Ding , Mahmoud Hassaballah , Karen Egiazarian , Wei-Fa Yang , Leszek Rutkowski

3D Gaussian Splatting (GS) enables highly photorealistic scene reconstruction from posed image sequences but struggles with viewpoint extrapolation due to its anisotropic nature, leading to overfitting and poor generalization, particularly…

计算机视觉与模式识别 · 计算机科学 2025-12-09 Shuohan Tao , Boyao Zhou , Hanzhang Tu , Yuwang Wang , Yebin Liu

The field of Novel View Synthesis has been revolutionized by 3D Gaussian Splatting (3DGS), which enables high-quality scene reconstruction that can be rendered in real-time. 3DGS-based techniques typically suffer from high GPU memory and…

图形学 · 计算机科学 2025-10-27 Umar Farooq , Jean-Yves Guillemaut , Adrian Hilton , Marco Volino

Capturing high-quality photographs under diverse real-world lighting conditions is challenging, as both natural lighting (e.g., low-light) and camera exposure settings (e.g., exposure time) significantly impact image quality. This challenge…

计算机视觉与模式识别 · 计算机科学 2025-04-24 Ziteng Cui , Xuangeng Chu , Tatsuya Harada

Recently, Gaussian Splatting methods have emerged as a desirable substitute for prior Radiance Field methods for novel-view synthesis of scenes captured with multi-view images or videos. In this work, we propose a novel extension to 4D…

计算机视觉与模式识别 · 计算机科学 2025-06-03 Karly Hou , Wanhua Li , Hanspeter Pfister

Differentiable rendering techniques have recently shown promising results for free-viewpoint video synthesis of characters. However, such methods, either Gaussian Splatting or neural implicit rendering, typically necessitate per-subject…

计算机视觉与模式识别 · 计算机科学 2024-11-19 Boyao Zhou , Shunyuan Zheng , Hanzhang Tu , Ruizhi Shao , Boning Liu , Shengping Zhang , Liqiang Nie , Yebin Liu