中文
相关论文

相关论文: SMASH: Physics-guided Reconstruction of Collisions…

200 篇论文

This work addresses the problem of recovering complete, simulatable object geometry from reconstructed real-world scenes, enabling physics-based interaction with objects embedded in the scene. While modern multi-view reconstruction methods…

计算机视觉与模式识别 · 计算机科学 2026-05-29 Xin Dong , Weijian Deng , Lihan Zhang , Tianru Dai , Wenfeng Deng , Yansong Tang

Human motion synthesis is an important problem with applications in graphics, gaming and simulation environments for robotics. Existing methods require accurate motion capture data for training, which is costly to obtain. Instead, we…

计算机视觉与模式识别 · 计算机科学 2022-08-15 Kevin Xie , Tingwu Wang , Umar Iqbal , Yunrong Guo , Sanja Fidler , Florian Shkurti

Collecting real-world vehicle accident videos for autonomous driving research is challenging due to their rarity and complexity. While existing driving video generation methods may produce visually realistic videos, they often fail to…

计算机视觉与模式识别 · 计算机科学 2026-04-14 Xiangwen Zhang , Qian Zhang , Longfei Han , Qiang Qu , Xiaoming Chen , Weidong Cai

Creating scenes for captured motions that achieve realistic human-scene interaction is crucial for 3D animation in movies or video games. As character motion is often captured in a blue-screened studio without real furniture or objects in…

计算机视觉与模式识别 · 计算机科学 2024-05-22 Jianan Li , Tao Huang , Qingxu Zhu , Tien-Tsin Wong

This paper presents an algorithm to reconstruct temporally consistent 3D meshes of deformable object instances from videos in the wild. Without requiring annotations of 3D mesh, 2D keypoints, or camera pose for each video frame, we pose…

计算机视觉与模式识别 · 计算机科学 2020-12-08 Xueting Li , Sifei Liu , Shalini De Mello , Kihwan Kim , Xiaolong Wang , Ming-Hsuan Yang , Jan Kautz

Videos from edited media like movies are a useful, yet under-explored source of information. The rich variety of appearance and interactions between humans depicted over a large temporal context in these films could be a valuable source of…

计算机视觉与模式识别 · 计算机科学 2020-12-18 Georgios Pavlakos , Jitendra Malik , Angjoo Kanazawa

Dynamic environments that include unstructured moving objects pose a hard problem for Simultaneous Localization and Mapping (SLAM) performance. The motion of rigid objects can be typically tracked by exploiting their texture and geometric…

计算机视觉与模式识别 · 计算机科学 2021-08-03 Huayan Zhang , Tianwei Zhang , Tin Lun Lam , Sethu Vijayakumar

We introduce a method to generate videos of dynamic virtual objects plausibly interacting via collisions with a still image's environment. Given a starting trajectory, physically simulated with the estimated geometry of a single, static…

计算机视觉与模式识别 · 计算机科学 2019-08-27 Carlo Innamorati , Bryan Russell , Danny M. Kaufman , and Niloy J. Mitra

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

Video synopsis, summarizing a video to generate a shorter video by exploiting the spatial and temporal redundancies, is important for surveillance and archiving. Existing trajectory-based video synopsis algorithms will not able to work in…

计算机视觉与模式识别 · 计算机科学 2024-01-08 Anton Jeran Ratnarajah , Sahani Goonetilleke , Dumindu Tissera , Kapilan Balagopalan , Ranga Rodrigo

We present a system that allows for accurate, fast, and robust estimation of camera parameters and depth maps from casual monocular videos of dynamic scenes. Most conventional structure from motion and monocular SLAM techniques assume input…

计算机视觉与模式识别 · 计算机科学 2024-12-10 Zhengqi Li , Richard Tucker , Forrester Cole , Qianqian Wang , Linyi Jin , Vickie Ye , Angjoo Kanazawa , Aleksander Holynski , Noah Snavely

Novel-view synthesis techniques achieve impressive results for static scenes but struggle when faced with the inconsistencies inherent to casual capture settings: varying illumination, scene motion, and other unintended effects that are…

Existing video generation models predominantly emphasize appearance fidelity while exhibiting limited ability to synthesize complex human motions, such as whole-body movements, long-range dynamics, and fine-grained human-environment…

计算机视觉与模式识别 · 计算机科学 2026-02-25 Haoyu Wang , Hao Tang , Donglin Di , Zhilu Zhang , Wangmeng Zuo , Feng Gao , Siwei Ma , Shiliang Zhang

Reconstructing dynamic scenes with large-scale and complex motions remains a significant challenge. Recent techniques like Neural Radiance Fields and 3D Gaussian Splatting (3DGS) have shown promise but still struggle with scenes involving…

计算机视觉与模式识别 · 计算机科学 2024-12-04 Qiankun Gao , Yanmin Wu , Chengxiang Wen , Jiarui Meng , Luyang Tang , Jie Chen , Ronggang Wang , Jian Zhang

Existing methods for reconstructing objects and humans from a monocular image suffer from severe mesh collisions and performance limitations for interacting occluding objects. This paper introduces a method to obtain a globally consistent…

计算机视觉与模式识别 · 计算机科学 2024-08-16 Sarthak Batra , Partha P. Chakrabarti , Simon Hadfield , Armin Mustafa

Video stabilization is essential for improving visual quality of shaky videos. The current video stabilization methods usually take feature trajectories in the background to estimate one global transformation matrix or several…

计算机视觉与模式识别 · 计算机科学 2020-06-16 Minda Zhao , Qiang Ling

Video data is more cost-effective than motion capture data for learning 3D character motion controllers, yet synthesizing realistic and diverse behaviors directly from videos remains challenging. Previous approaches typically rely on…

图形学 · 计算机科学 2025-12-10 Jianan Li , Xiao Chen , Tao Huang , Tien-Tsin Wong

Narrated instructional videos often show and describe manipulations of similar objects, e.g., repairing a particular model of a car or laptop. In this work we aim to reconstruct such objects and to localize associated narrations in 3D.…

计算机视觉与模式识别 · 计算机科学 2021-09-13 Dimitri Zhukov , Ignacio Rocco , Ivan Laptev , Josef Sivic , Johannes L. Schönberger , Bugra Tekin , Marc Pollefeys

We present UniSH, a unified, feed-forward framework for joint metric-scale 3D scene and human reconstruction. A key challenge in this domain is the scarcity of large-scale, annotated real-world data, forcing a reliance on synthetic…

计算机视觉与模式识别 · 计算机科学 2026-01-06 Mengfei Li , Peng Li , Zheng Zhang , Jiahao Lu , Chengfeng Zhao , Wei Xue , Qifeng Liu , Sida Peng , Wenxiao Zhang , Wenhan Luo , Yuan Liu , Yike Guo

Monocular dynamic reconstruction is a challenging and long-standing vision problem due to the highly ill-posed nature of the task. Existing approaches depend on templates, are effective only in quasi-static scenes, or fail to model 3D…

计算机视觉与模式识别 · 计算机科学 2025-10-17 Qianqian Wang , Vickie Ye , Hang Gao , Weijia Zeng , Jake Austin , Zhengqi Li , Angjoo Kanazawa
‹ 上一页 1 2 3 10 下一页 ›