Inspired by the success of volumetric 3D pose estima- tion, some recent human mesh estimators propose to esti- mate 3D skeletons as intermediate representations, from which, the dense 3D meshes are regressed by exploiting the mesh topology. However, body shape information is lost in extracting skeletons, leading to mediocre performance. The advanced motion capture systems solve the problem by placing dense physical markers on the body surface, which allows to extract realistic meshes from their non-rigid mo- tions. However, they cannot be applied to wild images without markers. In this work, we present an intermedi- ate representation, named virtual markers, which learns 64 landmark keypoints on the body surface based on the large-scale mocap data in a generative style, mimicking the effects of physical markers. The virtual markers can be ac- curately detected from wild images and can reconstruct the intact meshes with realistic shapes by simple interpolation. Our approach outperforms the state-of-the-art methods on three datasets. In particular, it surpasses the existing meth- ods by a notable margin on the SURREAL dataset, which has diverse body shapes.

Paper: https://arxiv.org/pdf/2303.11726.pdf

Project: https://shirleymaxx.github.io/virtual_marker/

Code：https://github.com/ShirleyMaxx/VirtualMarker

Video: https://www.youtube.com/watch?v=je2gNUiYl2c