BodyMap: Learning Full-Body Dense Correspondence Map

TL;DR

BodyMap introduces a novel deep learning framework using Vision Transformers to achieve high-definition, continuous dense correspondence between images of clothed humans and 3D models, enabling advanced full-body understanding and applications.

Contribution

The paper presents a new network architecture that learns continuous, fine-level body surface features, overcoming limitations of previous methods that used body part segmentation or single surface representations.

Findings

Outperforms prior methods on DensePose-COCO dataset

Achieves detailed correspondence including hands and hair

Enables applications like cloth mapping and neural rendering

Abstract

Dense correspondence between humans carries powerful semantic information that can be utilized to solve fundamental problems for full-body understanding such as in-the-wild surface matching, tracking and reconstruction. In this paper we present BodyMap, a new framework for obtaining high-definition full-body and continuous dense correspondence between in-the-wild images of clothed humans and the surface of a 3D template model. The correspondences cover fine details such as hands and hair, while capturing regions far from the body surface, such as loose clothing. Prior methods for estimating such dense surface correspondence i) cut a 3D body into parts which are unwrapped to a 2D UV space, producing discontinuities along part seams, or ii) use a single surface for representing the whole body, but none handled body details. Here, we introduce a novel network architecture with Vision Transformers that learn fine-level features on a continuous body surface. BodyMap outperforms prior work on various metrics and datasets, including DensePose-COCO by a large margin. Furthermore, we show various applications ranging from multi-layer dense cloth correspondence, neural rendering with novel-view synthesis and appearance swapping.