Abstract

We describe Human Mesh Recovery (HMR), an end-to-end framework for reconstructing a full 3D mesh of a human body from a single RGB image. In contrast to most current methods that compute 2D or 3D joint locations, we produce a richer and more useful mesh representation that is parameterized by shape and 3D joint angles. The main objective is to minimize the reprojection loss of keypoints, which allows our model to be trained using in-the-wild images that only have ground truth 2D annotations. However, the reprojection loss alone is highly underconstrained. In this work we address this problem by introducing an adversary trained to tell whether human body shape and pose parameters are real or not using a large database of 3D human meshes. We show that HMR can be trained with and without using any paired 2D-to-3D supervision. We do not rely on intermediate 2D keypoint detections and infer 3D pose and shape parameters directly from image pixels. Our model runs in real-time given a bounding box containing the person. We demonstrate our approach on various images in-the-wild and out-perform previous optimization-based methods that output 3D meshes and show competitive results on tasks such as 3D joint location estimation and part segmentation.

Keywords

Polygon meshComputer scienceArtificial intelligenceComputer visionMinimum bounding boxGround truthPoseSegmentationPixelParameterized complexity3d modelReprojection errorHuman-body modelSolid modelingBounding overwatchRGB color modelPoint cloudImage segmentationImage (mathematics)AlgorithmComputer graphics (images)

Affiliated Institutions

Related Publications

Publication Info

Year
2018
Type
article
Pages
7122-7131
Citations
1811
Access
Closed

External Links

Social Impact

Social media, news, blog, policy document mentions

Citation Metrics

1811
OpenAlex

Cite This

Angjoo Kanazawa, Michael J. Black, David W. Jacobs et al. (2018). End-to-End Recovery of Human Shape and Pose. , 7122-7131. https://doi.org/10.1109/cvpr.2018.00744

Identifiers

DOI
10.1109/cvpr.2018.00744