ShapeBoost: Boosting Human Shape Estimation with Part-Based Parameterization and Clothing-Preserving Augmentation

arXiv:2403.01345v1 Announce Type: new
Abstract: Accurate human shape recovery from a monocular RGB image is a challenging task because humans come in different shapes and sizes and wear different clothes. In this paper, we propose ShapeBoost, a new human shape recovery framework that achieves pixel-level alignment even for rare body shapes and high accuracy for people wearing different types of clothes. Unlike previous approaches that rely on the use of PCA-based shape coefficients, we adopt a new human shape parameterization …

abstract alignment arxiv augmentation boosting clothing cs.cv framework human humans image paper part pixel recovery type