Multiview-Consistent Semi-Supervised Learning for 3D Human Pose Estimation
This addresses the costly annotation requirements for 3D human pose estimation, offering a domain-specific incremental improvement.
The paper tackles the problem of reducing annotation dependency in 3D human pose estimation from monocular images by proposing a multiview-consistent semi-supervised learning framework, which improves the baseline by 25% and state-of-the-art by 8.7% while using smaller networks.
The best performing methods for 3D human pose estimation from monocular images require large amounts of in-the-wild 2D and controlled 3D pose annotated datasets which are costly and require sophisticated systems to acquire. To reduce this annotation dependency, we propose Multiview-Consistent Semi Supervised Learning (MCSS) framework that utilizes similarity in pose information from unannotated, uncalibrated but synchronized multi-view videos of human motions as additional weak supervision signal to guide 3D human pose regression. Our framework applies hard-negative mining based on temporal relations in multi-view videos to arrive at a multi-view consistent pose embedding. When jointly trained with limited 3D pose annotations, our approach improves the baseline by 25% and state-of-the-art by 8.7%, whilst using substantially smaller networks. Lastly, but importantly, we demonstrate the advantages of the learned embedding and establish view-invariant pose retrieval benchmarks on two popular, publicly available multi-view human pose datasets, Human 3.6M and MPI-INF-3DHP, to facilitate future research.