Parameter-Efficient Person Re-identification in the 3D Space

Understand

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 point clouds.