
This paper presents Key2Mesh, a model that efficiently estimates 3D human body meshes from 2D keypoint inputs by leveraging large-scale unpaired motion capture (MoCap) data and an adversarial domain adaptation technique to bridge the gap between MoCap and visual domains.


coremsg

efficient-3d-human-mesh-estimation-from-2d-keypoints-via-adversarial-domain-adaptation


Efficient 3D Human Mesh Estimation from 2D Keypoints via Adversarial Domain Adaptation


title_rewrite


LPSNet is the first end-to-end framework that can directly recover 3D human poses and shapes from lensless imaging measurements, without the need for intermediate image reconstruction.


lpsnet-end-to-end-human-pose-and-shape-estimation-from-lensless-imaging-measurements


LPSNet: End-to-End Human Pose and Shape Estimation from Lensless Imaging Measurements
