中文
相关论文

相关论文: 4D-VGGT: A General Foundation Model with SpatioTem…

200 篇论文

Reconstructing dynamic 4D scenes is challenging, as it requires robust disentanglement of dynamic objects from the static background. While 3D foundation models like VGGT provide accurate 3D geometry, their performance drops markedly when…

计算机视觉与模式识别 · 计算机科学 2025-11-26 Yu Hu , Chong Cheng , Sicheng Yu , Xiaoyang Guo , Hao Wang

Dynamic scene reconstruction in autonomous driving remains a fundamental challenge due to significant temporal variations, moving objects, and complex scene dynamics. Existing feed-forward 3D models have demonstrated strong performance in…

计算机视觉与模式识别 · 计算机科学 2026-03-10 Zhuolin He , Jing Li , Guanghao Li , Xiaolei Chen , Jiacheng Tang , Siyang Zhang , Zhounan Jin , Feipeng Cai , Bin Li , Jian Pu , Jia Cai , Xiangyang Xue

Recent 3D feed-forward models, such as the Visual Geometry Grounded Transformer (VGGT), have shown strong capability in inferring 3D attributes of static scenes. However, since they are typically trained on static datasets, these models…

计算机视觉与模式识别 · 计算机科学 2026-05-15 Kaichen Zhou , Yuhan Wang , Grace Chen , Xinhai Chang , Gaspard Beaudouin , Fangneng Zhan , Paul Pu Liang , Mengyu Wang

Reconstructing dynamic 4D scenes is an important yet challenging task. While 3D foundation models like VGGT excel in static settings, they often struggle with dynamic sequences where motion causes significant geometric ambiguity. To address…

计算机视觉与模式识别 · 计算机科学 2026-04-13 Ying Zang , Yidong Han , Chaotao Ding , Yuanqi Hu , Deyi Ji , Qi Zhu , Xuanfu Li , Jin Ma , Lingyun Sun , Tianrun Chen , Lanyun Zhu

We present a fast, spatio-temporal scene understanding framework based on Visual Geometry Grounded Transformer (VGGT). The proposed pipeline is designed to enable efficient, close to real-time performance, supporting applications including…

计算机视觉与模式识别 · 计算机科学 2025-12-01 Gergely Dinya , Péter Halász , András Lőrincz , Kristóf Karacs , Anna Gelencsér-Horváth

Reconstructing coherent 3D geometry and appearance from unposed multi-view images is a fundamental yet challenging problem in computer vision. Most existing visual geometry foundation models predict explicit geometry by regressing…

计算机视觉与模式识别 · 计算机科学 2026-05-22 Yuqi Wu , Tianyu Hu , Wenzhao Zheng , Yuanhui Huang , Haowen Sun , Jie Zhou , Jiwen Lu

Existing techniques for dynamic scene reconstruction from multiple wide-baseline cameras primarily focus on reconstruction in controlled environments, with fixed calibrated cameras and strong prior constraints. This paper introduces a…

计算机视觉与模式识别 · 计算机科学 2020-08-04 Armin Mustafa , Marco Volino , Hansung Kim , Jean-Yves Guillemaut , Adrian Hilton

Modeling dynamic, large-scale urban scenes is challenging due to their highly intricate geometric structures and unconstrained dynamics in both space and time. Prior methods often employ high-level architectural priors, separating static…

计算机视觉与模式识别 · 计算机科学 2025-08-26 Yurui Chen , Chun Gu , Junzhe Jiang , Xiatian Zhu , Li Zhang

Constructing 4D language fields is crucial for embodied AI, augmented/virtual reality, and 4D scene understanding, as they provide enriched semantic representations of dynamic environments and enable open-vocabulary querying in complex…

计算机视觉与模式识别 · 计算机科学 2025-12-05 Xianfeng Wu , Yajing Bai , Minghan Li , Xianzu Wu , Xueqi Zhao , Zhongyuan Lai , Wenyu Liu , Xinggang Wang

Reconstructing dynamic 4D scenes from monocular videos is a fundamental yet challenging task. While recent 3D foundation models provide strong geometric priors, their performance significantly degrades in dynamic environments. This…

计算机视觉与模式识别 · 计算机科学 2026-05-13 Ying Zang , Xuanyi Liu , Yidong Han , Deyi Ji , Chaotao Ding , Yuanqi Hu , Qi Zhu , Xuanfu Li , Jin Ma , Lingyun Sun , Tianrun Chen , Lanyun Zhu

Visual spatial description (VSD) aims to generate texts that describe the spatial relations of the given objects within images. Existing VSD work merely models the 2D geometrical vision features, thus inevitably falling prey to the problem…

计算机视觉与模式识别 · 计算机科学 2023-05-26 Yu Zhao , Hao Fei , Wei Ji , Jianguo Wei , Meishan Zhang , Min Zhang , Tat-Seng Chua

Feed-forward 3D foundation models face a key challenge: the quadratic computational cost introduced by global attention, which severely limits scalability as input length increases. Concurrent acceleration methods, such as token merging,…

计算机视觉与模式识别 · 计算机科学 2026-03-19 Xinze Li , Pengxu Chen , Yiyuan Wang , Weifeng Su , Wentao Cheng

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

We present VGGT, a feed-forward neural network that directly infers all key 3D attributes of a scene, including camera parameters, point maps, depth maps, and 3D point tracks, from one, a few, or hundreds of its views. This approach is a…

计算机视觉与模式识别 · 计算机科学 2025-03-17 Jianyuan Wang , Minghao Chen , Nikita Karaev , Andrea Vedaldi , Christian Rupprecht , David Novotny

Recent advancements in dynamic 3D scene reconstruction have shown promising results, enabling high-fidelity 3D novel view synthesis with improved temporal consistency. Among these, 4D Gaussian Splatting (4DGS) has emerged as an appealing…

计算机视觉与模式识别 · 计算机科学 2025-05-20 Seungjun Oh , Younggeun Lee , Hyejin Jeon , Eunbyung Park

Recent approaches on visual scene understanding attempt to build a scene graph -- a computational representation of objects and their pairwise relationships. Such rich semantic representation is very appealing, yet difficult to obtain from…

计算机视觉与模式识别 · 计算机科学 2018-11-08 Paul Gay , Stuart James , Alessio Del Bue

Generating a coherent 3D scene representation from multi-view images is a fundamental yet challenging task. Existing methods often struggle with multi-view fusion, leading to fragmented 3D representations and sub-optimal performance. To…

计算机视觉与模式识别 · 计算机科学 2025-12-09 Junho Kim , Seongwon Lee

Due to the complex and highly dynamic motions in the real world, synthesizing dynamic videos from multi-view inputs for arbitrary viewpoints is challenging. Previous works based on neural radiance field or 3D Gaussian splatting are limited…

计算机视觉与模式识别 · 计算机科学 2025-07-04 Jiahao Wu , Rui Peng , Jianbo Jiao , Jiayu Yang , Luyang Tang , Kaiqiang Xiong , Jie Liang , Jinbo Yan , Runling Liu , Ronggang Wang

Perceiving and reconstructing 3D scene geometry from visual inputs is crucial for autonomous driving. However, there still lacks a driving-targeted dense geometry perception model that can adapt to different scenarios and camera…

计算机视觉与模式识别 · 计算机科学 2025-12-19 Sicheng Zuo , Zixun Xie , Wenzhao Zheng , Shaoqing Xu , Fang Li , Shengyin Jiang , Long Chen , Zhi-Xin Yang , Jiwen Lu

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
‹ 上一页 1 2 3 10 下一页 ›