MicrosoftAsia-Densely Semantically Aligned Person Re-Identification

Abstract

爲啥牽扯UV空間和texture image

因爲引入3D body surface後, each position on the 3D body surface(而不是在原來的圖像) has a semantic identity (identified by a 2D coordinate$(u,v) $ in UV space) and a texture representation.

意思每個點都有對應的語義標識和紋理表達。