Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation
This addresses the problem of efficient and accurate 3D pose estimation for multiple persons in computer vision, with incremental improvements in speed and performance.
The paper tackles multi-person 3D pose estimation by proposing a Distribution-Aware Single-stage (DAS) model that simultaneously localizes person positions and body joints in 3D space, achieving a 1.5x speedup over previous models and state-of-the-art accuracy on benchmarks like CMU Panoptic and MuPoTS-3D.
In this paper, we present a novel Distribution-Aware Single-stage (DAS) model for tackling the challenging multi-person 3D pose estimation problem. Different from existing top-down and bottom-up methods, the proposed DAS model simultaneously localizes person positions and their corresponding body joints in the 3D camera space in a one-pass manner. This leads to a simplified pipeline with enhanced efficiency. In addition, DAS learns the true distribution of body joints for the regression of their positions, rather than making a simple Laplacian or Gaussian assumption as previous works. This provides valuable priors for model prediction and thus boosts the regression-based scheme to achieve competitive performance with volumetric-base ones. Moreover, DAS exploits a recursive update strategy for progressively approaching to regression target, alleviating the optimization difficulty and further lifting the regression performance. DAS is implemented with a fully Convolutional Neural Network and end-to-end learnable. Comprehensive experiments on benchmarks CMU Panoptic and MuPoTS-3D demonstrate the superior efficiency of the proposed DAS model, specifically 1.5x speedup over previous best model, and its stat-of-the-art accuracy for multi-person 3D pose estimation.