Abstract: We propose a multi-view weakly-supervised 3D human pose estimation network. In this network, we fuse multi-view features and generate the final 3D pose, supervising the 3D pose using human ...

Abstract: Estimating 3D human pose from 2D images in real world contexts remains a challenge, characterized by unique data constraints. Large general datasets of motion-captured 3D adult human poses ...

Official implementation of our CleanPose, the first solution to mitigate the confoundering effect in category-level pose estimation via causal learning and knowledge distillation. You can generate the ...

FMPose3D creates a 3D pose from a single 2D image. It leverages fast Flow Matching, generating multiple plausible 3D poses via an ODE in just a few steps, then aggregates them using a ...