Estimating human pose and shape from monocular images is a long-standing problem in
computer vision. Since the release of statistical body models, 3D human mesh recovery has …

Top-down methods dominate the field of 3D human pose and shape estimation, because
they are decoupled from human detection and allow researchers to focus on the core …

Estimating 3D humans from images often produces implausible bodies that lean, float, or
penetrate the floor. Such methods ignore the fact that bodies are typically supported by the …

We present PyMAF-X, a regression-based approach to recovering a parametric full-body
model from a single image. This task is very challenging since minor parametric deviation …

We propose a method to reconstruct global human trajectories from videos in the wild. Our
optimization method decouples the camera and human motion, which allows us to place …

This paper focuses on the regression of multiple 3D people from a single RGB image.
Existing approaches predominantly follow a multi-stage pipeline that first detects people in …

Existing 3D human pose estimators suffer poor generalization performance to new datasets,
largely due to the limited diversity of 2D-3D pose pairs in the training data. To address this …

We present an approach for 3D global human mesh recovery from monocular videos
recorded with dynamic cameras. Our approach is robust to severe and long-term occlusions …

Top-down methods for monocular human mesh recovery have two stages:(1) detect human
bounding boxes;(2) treat each bounding box as an independent single-human mesh …

Abstract 3D understanding and rendering of moving humans from monocular videos is a
challenging task. Although recent progress has enabled this task to some extent, it is still …