Probabilistic Modeling for Human Mesh Recovery

This paper focuses on the problem of 3D human reconstruction from 2D evidence. Although this is an inherently ambiguous problem, the majority of recent works avoid the uncertainty modeling and typically regress a single estimate for a given input. In contrast to that, in this work, we propose to embrace the reconstruction ambiguity and we recast the problem as learning a mapping from the input to a distribution of plausible 3D poses. Our approach is based on the normalizing flows model and offers a series of advantages. For conventional applications, where a single 3D estimate is required, our formulation allows for efficient mode computation. Using the mode leads to performance that is comparable with the state of the art among deterministic unimodal regression models. Simultaneously, since we have access to the likelihood of each sample, we demonstrate that our model is useful in a series of downstream tasks, where we leverage the probabilistic nature of the prediction as a tool for more accurate estimation. These tasks include reconstruction from multiple uncalibrated views, as well as human model fitting, where our model acts as a powerful image-based prior for mesh recovery. Our results validate the importance of probabilistic modeling, and indicate state-of-the-art performance across a variety of settings. Code and models are available at:

PDF Abstract ICCV 2021 PDF ICCV 2021 Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
3D Human Pose Estimation 3DPW ProHMR + fitting PA-MPJPE 55.1 # 91
3D Human Pose Estimation 3DPW ProHMR PA-MPJPE 65 # 116
3D Human Pose Estimation 3DPW Biggs [3] PA-MPJPE 59.9 # 105
3D Human Pose Estimation Human3.6M ProHMR PA-MPJPE 41.2 # 73