English
Related papers

Related papers: STGFormer: Spatio-Temporal GraphFormer for 3D Huma…

200 papers

Accurate 3D human pose estimation from monocular videos requires effective modelling of complex spatial and temporal dependencies. However, existing methods often face challenges in efficiency and adaptability when modelling spatial and…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Ruochen Li , Shuang Chen , Wenke E , Farshad Arvin , Amir Atapour-Abarghouei

We propose a novel Transformer-based architecture for the task of generative modelling of 3D human motion. Previous work commonly relies on RNN-based models considering shorter forecast horizons reaching a stationary and often implausible…

Computer Vision and Pattern Recognition · Computer Science 2021-11-30 Emre Aksan , Manuel Kaufmann , Peng Cao , Otmar Hilliges

Despite the recent progress, 3D multi-person pose estimation from monocular videos is still challenging due to the commonly encountered problem of missing information caused by occlusion, partially out-of-frame target persons, and…

Computer Vision and Pattern Recognition · Computer Science 2021-04-08 Yu Cheng , Bo Wang , Bo Yang , Robby T. Tan

Recovering temporally consistent 3D human body pose, shape and motion from a monocular video is a challenging task due to (self-)occlusions, poor lighting conditions, complex articulated body poses, depth ambiguity, and limited availability…

Computer Vision and Pattern Recognition · Computer Science 2023-11-21 Sushovan Chanda , Amogh Tiwari , Lokender Tiwari , Brojeshwar Bhowmick , Avinash Sharma , Hrishav Barua

Recent transformer-based approaches have demonstrated excellent performance in 3D human pose estimation. However, they have a holistic view and by encoding global relationships between all the joints, they do not capture the local…

Computer Vision and Pattern Recognition · Computer Science 2023-10-26 Soroush Mehraban , Vida Adeli , Babak Taati

Estimating 3D human poses from a monocular video is still a challenging task. Many existing methods' performance drops when the target person is occluded by other objects, or the motion is too fast/slow relative to the scale and speed of…

Computer Vision and Pattern Recognition · Computer Science 2020-10-20 Cheng Yu , Bo Wang , Bo Yang , Robby T. Tan

2D-to-3D human pose lifting is fundamental for 3D human pose estimation (HPE), for which graph convolutional networks (GCNs) have proven inherently suitable for modeling the human skeletal topology. However, the current GCN-based 3D HPE…

Computer Vision and Pattern Recognition · Computer Science 2023-10-31 Kai Zhai , Qiang Nie , Bo Ouyang , Xiang Li , Shanlin Yang

While head-mounted devices are becoming more compact, they provide egocentric views with significant self-occlusions of the device user. Hence, existing methods often fail to accurately estimate complex 3D poses from egocentric views. In…

Computer Vision and Pattern Recognition · Computer Science 2024-05-16 Hiroyasu Akada , Jian Wang , Vladislav Golyanik , Christian Theobalt

Reconstructing 3D human pose and shape from monocular videos is a well-studied but challenging problem. Common challenges include occlusions, the inherent ambiguities in the 2D to 3D mapping and the computational complexity of video…

Computer Vision and Pattern Recognition · Computer Science 2023-05-02 Nikolaos Vasilikopoulos , Nikos Kolotouros , Aggeliki Tsoli , Antonis Argyros

Transformer-based methods have recently achieved significant success in 3D human pose estimation, owing to their strong ability to model long-range dependencies. However, relying solely on the global attention mechanism is insufficient for…

Computer Vision and Pattern Recognition · Computer Science 2024-12-30 Guangsheng Xu , Guoyi Zhang , Lejia Ye , Shuwei Gan , Xiaohu Zhang , Xia Yang

Recent multi-frame lifting methods have dominated the 3D human pose estimation. However, previous methods ignore the intricate dependence within the 2D pose sequence and learn single temporal correlation. To alleviate this limitation, we…

Computer Vision and Pattern Recognition · Computer Science 2025-01-06 Jiajie Liu , Mengyuan Liu , Hong Liu , Wenhao Li

Recently, fully-transformer architectures have replaced the defacto convolutional architecture for the 3D human pose estimation task. In this paper we propose \textbf{\textit{ConvFormer}}, a novel convolutional transformer that leverages a…

Computer Vision and Pattern Recognition · Computer Science 2023-04-06 Alec Diaz-Arias , Dmitriy Shin

In this paper, a self-supervised model that simultaneously predicts a sequence of future frames from video-input with a novel spatial-temporal attention (ST) network is proposed. The ST transformer network allows constraining both temporal…

Computer Vision and Pattern Recognition · Computer Science 2023-03-03 Houssem Boulahbal , Adrian Voicila , Andrew Comport

Existing marker-less motion capture methods often assume known backgrounds, static cameras, and sequence specific motion priors, which narrows its application scenarios. Here we propose a fully automatic method that given multi-view video,…

Computer Vision and Pattern Recognition · Computer Science 2018-05-01 Yinghao Huang , Federica Bogo , Christoph Lassner , Angjoo Kanazawa , Peter V. Gehler , Ijaz Akhter , Michael J. Black

The dominant paradigm in 3D human pose estimation that lifts a 2D pose sequence to 3D heavily relies on long-term temporal clues (i.e., using a daunting number of video frames) for improved accuracy, which incurs performance saturation,…

Computer Vision and Pattern Recognition · Computer Science 2023-11-10 Qitao Zhao , Ce Zheng , Mengyuan Liu , Chen Chen

Temporal modeling and spatio-temporal collaboration are pivotal techniques for video-based human pose estimation. Most state-of-the-art methods adopt optical flow or temporal difference, learning local visual content correspondence across…

Computer Vision and Pattern Recognition · Computer Science 2025-02-18 Runyang Feng , Haoming Chen

Human motion prediction (HMP) involves forecasting future human motion based on historical data. Graph Convolutional Networks (GCNs) have garnered widespread attention in this field for their proficiency in capturing relationships among…

Computer Vision and Pattern Recognition · Computer Science 2025-01-03 Jiexin Wang , Yiju Guo , Bing Su

We introduce HuMoR: a 3D Human Motion Model for Robust Estimation of temporal pose and shape. Though substantial progress has been made in estimating 3D human motion and shape from dynamic observations, recovering plausible pose sequences…

Computer Vision and Pattern Recognition · Computer Science 2021-08-19 Davis Rempe , Tolga Birdal , Aaron Hertzmann , Jimei Yang , Srinath Sridhar , Leonidas J. Guibas

Learning to capture human motion is essential to 3D human pose and shape estimation from monocular video. However, the existing methods mainly rely on recurrent or convolutional operation to model such temporal information, which limits the…

Computer Vision and Pattern Recognition · Computer Science 2022-03-17 Wen-Li Wei , Jen-Chun Lin , Tyng-Luh Liu , Hong-Yuan Mark Liao

Recently, transformer-based methods have gained significant success in sequential 2D-to-3D lifting human pose estimation. As a pioneering work, PoseFormer captures spatial relations of human joints in each video frame and human dynamics…

Computer Vision and Pattern Recognition · Computer Science 2023-03-31 Qitao Zhao , Ce Zheng , Mengyuan Liu , Pichao Wang , Chen Chen