English
Related papers

Related papers: Epipolar Transformers

200 papers

Exploiting relations among 2D joints plays a crucial role yet remains semi-developed in 2D-to-3D pose estimation. To alleviate this issue, we propose GraFormer, a novel transformer architecture combined with graph convolution for 3D pose…

Computer Vision and Pattern Recognition · Computer Science 2021-09-20 Weixi Zhao , Yunjie Tian , Qixiang Ye , Jianbin Jiao , Weiqiang Wang

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

Current human pose estimation systems focus on retrieving an accurate 3D global estimate of a single person. Therefore, this paper presents one of the first 3D multi-person human pose estimation systems that is able to work in real-time and…

Computer Vision and Pattern Recognition · Computer Science 2024-03-15 Pawel Knap , Peter Hardy , Alberto Tamajo , Hwasup Lim , Hansung Kim

Contemporary approaches to solving various problems that require analyzing three-dimensional (3D) meshes and point clouds have adopted the use of deep learning algorithms that directly process 3D data such as point coordinates, normal…

Computer Vision and Pattern Recognition · Computer Science 2024-07-12 Stefan Novaković , Vladimir Risojević

We propose to estimate 3D human pose from multi-view images and a few IMUs attached at person's limbs. It operates by firstly detecting 2D poses from the two signals, and then lifting them to the 3D space. We present a geometric approach to…

Computer Vision and Pattern Recognition · Computer Science 2020-04-13 Zhe Zhang , Chunyu Wang , Wenhu Qin , Wenjun Zeng

With the explosive growth of available training data, single-image 3D human modeling is ahead of a transition to a data-centric paradigm. A key to successfully exploiting data scale is to design flexible models that can be supervised from…

Computer Vision and Pattern Recognition · Computer Science 2024-12-11 István Sárándi , Gerard Pons-Moll

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

Recognition of human poses and actions is crucial for autonomous systems to interact smoothly with people. However, cameras generally capture human poses in 2D as images and videos, which can have significant appearance variations across…

Computer Vision and Pattern Recognition · Computer Science 2021-11-19 Ting Liu , Jennifer J. Sun , Long Zhao , Jiaping Zhao , Liangzhe Yuan , Yuxiao Wang , Liang-Chieh Chen , Florian Schroff , Hartwig Adam

Feature learning for 3D object detection from point clouds is very challenging due to the irregularity of 3D point cloud data. In this paper, we propose Pointformer, a Transformer backbone designed for 3D point clouds to learn features…

Computer Vision and Pattern Recognition · Computer Science 2021-06-23 Xuran Pan , Zhuofan Xia , Shiji Song , Li Erran Li , Gao Huang

3D human pose estimation (HPE) is crucial in many fields, such as human behavior analysis, augmented reality/virtual reality (AR/VR) applications, and self-driving industry. Videos that contain multiple potentially occluded people captured…

Computer Vision and Pattern Recognition · Computer Science 2020-11-03 Renshu Gu , Gaoang Wang , Jenq-Neng Hwang

Existing Transformers for monocular 3D human shape and pose estimation typically have a quadratic computation and memory complexity with respect to the feature length, which hinders the exploitation of fine-grained information in…

Computer Vision and Pattern Recognition · Computer Science 2024-04-24 Xiangyu Xu , Lijuan Liu , Shuicheng Yan

We consider the task of 3D joints location and orientation prediction from a monocular video with the skinned multi-person linear (SMPL) model. We first infer 2D joints locations with an off-the-shelf pose estimation algorithm. We use the…

Computer Vision and Pattern Recognition · Computer Science 2020-09-15 Imry Kissos , Lior Fritz , Matan Goldman , Omer Meir , Eduard Oks , Mark Kliger

Video 3D human pose estimation aims to localize the 3D coordinates of human joints from videos. Recent transformer-based approaches focus on capturing the spatiotemporal information from sequential 2D poses, which cannot model the…

Computer Vision and Pattern Recognition · Computer Science 2022-08-09 Zhongwei Qiu , Qiansheng Yang , Jian Wang , Dongmei Fu

Accurate and real-time three-dimensional (3D) pose estimation is challenging in resource-constrained and dynamic environments owing to its high computational complexity. To address this issue, this study proposes a novel cooperative…

Computer Vision and Pattern Recognition · Computer Science 2025-04-07 Hyun-Ho Choi , Kangsoo Kim , Ki-Ho Lee , Kisong Lee

HybrIK relies on a combination of analytical inverse kinematics and deep learning to produce more accurate 3D pose estimation from 2D monocular images. HybrIK has three major components: (1) pretrained convolution backbone, (2)…

Computer Vision and Pattern Recognition · Computer Science 2023-04-25 Boris N. Oreshkin

3D hand pose estimation (HPE) is the process of locating the joints of the hand in 3D from any visual input. HPE has recently received an increased amount of attention due to its key role in a variety of human-computer interaction…

Computer Vision and Pattern Recognition · Computer Science 2022-06-14 Leyla Khaleghi , Joshua Marshall , Ali Etemad

Conventional 3D human pose estimation relies on first detecting 2D body keypoints and then solving the 2D to 3D correspondence problem.Despite the promising results, this learning paradigm is highly dependent on the quality of the 2D…

Computer Vision and Pattern Recognition · Computer Science 2021-12-22 Jue Wang , Shaoli Huang , Xinchao Wang , Dacheng Tao

Multi-view multi-person 3D pose estimation in team sports scenarios remains challenging due to player occlusions, appearance similarity caused by team uniforms, and the scarcity of annotated multi-view data, all of which limit the…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Li Yin , Qin Haobin , Tomohiro Suzuki , Calvin Yeung , Mariko Isogawa , Keisuke Fujii

We address the challenge of accurate 3D human pose and shape estimation from monocular images. The key to accuracy and robustness lies in high-quality training data. Existing training datasets containing real images with pseudo ground truth…

Computer Vision and Pattern Recognition · Computer Science 2024-11-14 Priyanka Patel , Michael J. Black

Although monocular 3D human pose estimation methods have made significant progress, it is far from being solved due to the inherent depth ambiguity. Instead, exploiting multi-view information is a practical way to achieve absolute 3D human…

Computer Vision and Pattern Recognition · Computer Science 2022-05-18 Guoliang Hua , Hong Liu , Wenhao Li , Qian Zhang , Runwei Ding , Xin Xu