中文
相关论文

相关论文: SAM4Dcap: Training-free Biomechanical Twin System …

200 篇论文

Quantifying human movement (kinematics) and musculoskeletal forces (kinetics) at scale, such as estimating quadriceps force during a sit-to-stand movement, could transform prediction, treatment, and monitoring of mobility-related…

计算机视觉与模式识别 · 计算机科学 2026-03-27 Selim Gilon , Emily Y. Miller , Scott D. Uhlrich

Human Mesh Recovery (HMR) aims to reconstruct 3D human pose and shape from 2D observations and is fundamental to human-centric understanding in real-world scenarios. While recent image-based HMR methods such as SAM 3D Body achieve strong…

计算机视觉与模式识别 · 计算机科学 2025-12-10 Mingqi Gao , Yunqi Miao , Jungong Han

Accurate hand and finger tracking from video has significant clinical applications for monitoring activities of daily living and measuring range of motion, yet monocular video approaches for obtaining hand biomechanics remain…

计算机视觉与模式识别 · 计算机科学 2026-05-12 R. James Cotton , Pouyan Firouzabadi , Wendy Murray

Understanding human motion beyond surface kinematics is crucial for motion analysis, rehabilitation, and injury risk assessment. However, progress in this domain is limited by the lack of large-scale datasets with biomechanical annotations,…

计算机视觉与模式识别 · 计算机科学 2026-05-15 Yujun Huo , He Zhang , Chentao Song , Honglin Song , Zongyu Zuo , Tao Yu

We present the first marker-less approach for temporally coherent 3D performance capture of a human with general clothing from monocular video. Our approach reconstructs articulated human skeleton motion as well as medium-scale non-rigid…

计算机视觉与模式识别 · 计算机科学 2018-02-26 Weipeng Xu , Avishek Chatterjee , Michael Zollhöfer , Helge Rhodin , Dushyant Mehta , Hans-Peter Seidel , Christian Theobalt

We present a self-supervised learning-based pipeline for dense 3D reconstruction from full-length monocular endoscopic videos without a priori modeling of anatomy or shading. Our method only relies on unlabeled monocular endoscopic videos…

计算机视觉与模式识别 · 计算机科学 2019-09-10 Xingtong Liu , Ayushi Sinha , Masaru Ishii , Gregory D. Hager , Russell H. Taylor , Mathias Unberath

Markerless motion capture and understanding of professional non-daily human movements is an important yet unsolved task, which suffers from complex motion patterns and severe self-occlusion, especially for the monocular setting. In this…

计算机视觉与模式识别 · 计算机科学 2021-07-19 Xin Chen , Anqi Pang , Wei Yang , Yuexin Ma , Lan Xu , Jingyi Yu

Reconstructing biomechanically realistic 3D human motion - recovering both kinematics (motion) and kinetics (forces) - is a critical challenge. While marker-based systems are lab-bound and slow, popular monocular methods use oversimplified,…

计算机视觉与模式识别 · 计算机科学 2025-11-25 Farnoosh Koleini , Hongfei Xue , Ahmed Helmy , Pu Wang

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

Learning robust and scalable visual representations from massive multi-view video data remains a challenge in computer vision and autonomous driving. Existing pre-training methods either rely on expensive supervised learning with 3D…

计算机视觉与模式识别 · 计算机科学 2024-03-14 Jialv Zou , Bencheng Liao , Qian Zhang , Wenyu Liu , Xinggang Wang

SAM 3D Body (3DB) achieves state-of-the-art accuracy in monocular 3D human mesh recovery, yet its inference latency of several seconds per image precludes real-time application. We present Fast SAM 3D Body, a training-free acceleration…

计算机视觉与模式识别 · 计算机科学 2026-03-17 Timing Yang , Sicheng He , Hongyi Jing , Jiawei Yang , Zhijian Liu , Chuhang Zou , Yue Wang

This work aims to discuss the current landscape of kinematic analysis tools, ranging from the state-of-the-art in sports biomechanics such as inertial measurement units (IMUs) and retroreflective marker-based optical motion capture (MoCap)…

计算机视觉与模式识别 · 计算机科学 2025-03-20 Kai Armstrong , Alexander Rodrigues , Alexander P. Willmott , Lei Zhang , Xujiong Ye

We propose Mesh4D, a feed-forward model for monocular 4D mesh reconstruction. Given a monocular video of a dynamic object, our model reconstructs the object's complete 3D shape and motion, represented as a deformation field. Our key…

计算机视觉与模式识别 · 计算机科学 2026-01-09 Zeren Jiang , Chuanxia Zheng , Iro Laina , Diane Larlus , Andrea Vedaldi

Video and wearable sensor data provide complementary information about human movement. Video provides a holistic understanding of the entire body in the world while wearable sensors provide high-resolution measurements of specific body…

计算机视觉与模式识别 · 计算机科学 2024-11-18 J. D. Peiffer , Kunal Shah , Shawana Anarwala , Kayan Abdou , R. James Cotton

This paper presents a biomechanically interpretable framework for gait analysis using 3D human reconstruction from video data. Unlike conventional keypoint based approaches, the proposed method extracts biomechanically meaningful markers…

图像与视频处理 · 电气工程与系统科学 2026-03-04 Akila Pemasiri , Ethan Goan , Glen Lichtwark , Robert Schuster , Luke Kelly , Clinton Fookes

We present the first real-time human performance capture approach that reconstructs dense, space-time coherent deforming geometry of entire humans in general everyday clothing from just a single RGB video. We propose a novel two-stage…

计算机视觉与模式识别 · 计算机科学 2019-01-28 Marc Habermann , Weipeng Xu , Michael Zollhoefer , Gerard Pons-Moll , Christian Theobalt

Markerless estimation of 3D Kinematics has the great potential to clinically diagnose and monitor movement disorders without referrals to expensive motion capture labs; however, current approaches are limited by performing multiple…

计算机视觉与模式识别 · 计算机科学 2023-01-16 Marian Bittner , Wei-Tse Yang , Xucong Zhang , Ajay Seth , Jan van Gemert , Frans C. T. van der Helm

We present SAM4D, a multi-modal and temporal foundation model designed for promptable segmentation across camera and LiDAR streams. Unified Multi-modal Positional Encoding (UMPE) is introduced to align camera and LiDAR features in a shared…

计算机视觉与模式识别 · 计算机科学 2025-06-27 Jianyun Xu , Song Wang , Ziqian Ni , Chunyong Hu , Sheng Yang , Jianke Zhu , Qiang Li

Reconstructing 4D dynamic scenes from casually captured monocular videos is valuable but highly challenging, as each timestamp is observed from a single viewpoint. We introduce Vivid4D, a novel approach that enhances 4D monocular video…

计算机视觉与模式识别 · 计算机科学 2025-04-21 Jiaxin Huang , Sheng Miao , BangBang Yang , Yuewen Ma , Yiyi Liao

Recovering a dense 3D body mesh from monocular video remains challenging under occlusion from draping and continuously moving camera viewpoints. This configuration arises in surgical augmented reality (AR), where an anesthetized patient…

计算机视觉与模式识别 · 计算机科学 2026-03-19 Mingxiao Tu , Hoijoon Jung , Alireza Moghadam , Andre Kyme , Jinman Kim
‹ 上一页 1 2 3 10 下一页 ›