A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is
People live in a 3D world. However, existing works on person re-identification (re-id) mostly consider the semantic representation learning in a 2D space, intrinsically limiting the understanding of people. In this work, we address this limitation by exploring the prior knowledge of the 3D body structure. Specifically, we project 2D images to a 3D space and introduce a novel parameter-efficient Omni-scale Graph Network (OG-Net) to learn the pedestrian representation directly from 3D pointarXiv:2006.04569v3 fatcat:4bjdlqpuvzendmg5xehnidpw4m