Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

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

About

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.

Siyuan Bian, Jiefeng Li, Jiasheng Tang, Cewu Lu• 2024

Related benchmarks

TaskDatasetResultRank
3D Human Mesh Recovery3DPW (test)
MPJPE75.3
341
3D Human Shape EstimationSSP-3D (test)
PVE (T-SC)11.4
54
Showing 2 of 2 rows

Other info

Follow for update