Adversarial 3D Human Pose Estimation via Multimodal Depth Supervision
It addresses the problem of accurate 3D pose reconstruction for computer vision applications, but appears incremental as it builds on existing methods like depth extraction and adversarial schemes.
The paper tackles 3D human pose estimation from a single image by proposing a two-phase deep-learning framework that uses multimodal depth supervision and adversarial training, achieving an MPJPE of 58.68mm on the ECCV2018 challenge.
In this paper, a novel deep-learning based framework is proposed to infer 3D human poses from a single image. Specifically, a two-phase approach is developed. We firstly utilize a generator with two branches for the extraction of explicit and implicit depth information respectively. During the training process, an adversarial scheme is also employed to further improve the performance. The implicit and explicit depth information with the estimated 2D joints generated by a widely used estimator, in the second step, are together fed into a deep 3D pose regressor for the final pose generation. Our method achieves MPJPE of 58.68mm on the ECCV2018 3D Human Pose Estimation Challenge.