Keypoint transformer: Solving joint identification in challenging hands and object interactions for accurate 3d pose estimation

S Hampali, SD Sarkar, M Rad… - Proceedings of the …, 2022 - openaccess.thecvf.com
We propose a robust and accurate method for estimating the 3D poses of two hands in close
interaction from a single color image. This is a very challenging problem, as large occlusions …

Model-based 3d hand reconstruction via self-supervised learning

Y Chen, Z Tu, D Kang, L Bao, Y Zhang… - Proceedings of the …, 2021 - openaccess.thecvf.com
Reconstructing a 3D hand from a single-view RGB image is challenging due to various hand
configurations and depth ambiguity. To reliably reconstruct a 3D hand from a monocular …

Weakly supervised 3d hand pose estimation via biomechanical constraints

A Spurr, U Iqbal, P Molchanov, O Hilliges… - European conference on …, 2020 - Springer
Estimating 3D hand pose from 2D images is a difficult, inverse problem due to the inherent
scale and depth ambiguities. Current state-of-the-art methods train fully supervised deep …

A2j-transformer: Anchor-to-joint transformer network for 3d interacting hand pose estimation from a single rgb image

C Jiang, Y **ao, C Wu, M Zhang… - Proceedings of the …, 2023 - openaccess.thecvf.com
Abstract 3D interacting hand pose estimation from a single RGB image is a challenging task,
due to serious self-occlusion and inter-occlusion towards hands, confusing similar …

End-to-end detection and pose estimation of two interacting hands

DU Kim, KI Kim, S Baek - Proceedings of the IEEE/CVF …, 2021 - openaccess.thecvf.com
Three dimensional hand pose estimation has reached a level of maturity, enabling real-
world applications for single-hand cases. However, accurate estimation of the pose of two …

Showme: Benchmarking object-agnostic hand-object 3d reconstruction

A Swamy, V Leroy, P Weinzaepfel… - Proceedings of the …, 2023 - openaccess.thecvf.com
Recent hand-object interaction datasets show limited real object variability and rely on fitting
the MANO parametric model to obtain groundtruth hand shapes. To go beyond these …

Visual-inertial hand motion tracking with robustness against occlusion, interference, and contact

Y Lee, W Do, H Yoon, J Heo, WH Lee, D Lee - Science Robotics, 2021 - science.org
State-of-the-art technologies for hand (and finger) motion tracking do not always provide
accurate and robust tracking. For example, severe occlusions can affect tracking with vision …

Two heads are better than one: Image-point cloud network for depth-based 3d hand pose estimation

P Ren, Y Chen, J Hao, H Sun, Q Qi, J Wang… - Proceedings of the AAAI …, 2023 - ojs.aaai.org
Depth images and point clouds are the two most commonly used data representations for
depth-based 3D hand pose estimation. Benefiting from the structuring of image data and the …

I2uv-handnet: Image-to-uv prediction network for accurate and high-fidelity 3d hand mesh modeling

P Chen, Y Chen, D Yang, F Wu, Q Li… - Proceedings of the …, 2021 - openaccess.thecvf.com
Reconstructing a high-precision and high-fidelity 3D human hand from a color image plays a
central role in replicating a realistic virtual hand in human-computer interaction and virtual …