This repository provides the official PyTorch implementation of a 2019 ICCV paper on camera distance-aware top-down 3D multi-person pose estimation. The model uses deep learning to detect and estimate 3D positions of human joints (skeleton keypoints) from a single RGB image. It supports multiple benchmark datasets including Human3.6M, MPII, MS COCO 2017, MuCo-3DHP, and MuPoTS-3D, and includes visualization utilities for pose estimation results.