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

Author:

Siyuan Bian, Jiefeng Li, Jiasheng Tang, Cewu Lu

Keyword:

Computer Science, Computer Vision and Pattern Recognition, Computer Vision and Pattern Recognition (cs.CV)

journal:

date:

2024-03-02 00:00:00

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 that decomposes the human shape into bone lengths and the mean width of each part slice. This part-based parameterization technique achieves a balance between flexibility and validity using a semi-analytical shape reconstruction algorithm. Based on this new parameterization, a clothing-preserving data augmentation module is proposed to generate realistic images with diverse body shapes and accurate annotations. Experimental results show that our method outperforms other state-of-the-art methods in diverse body shape situations as well as in varied clothing situations.

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