Saved in:
Bibliographic Details
Main Authors: Bian, Siyuan, Li, Jiefeng, Tang, Jiasheng, Lu, Cewu
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.01345
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909126047563776
author Bian, Siyuan
Li, Jiefeng
Tang, Jiasheng
Lu, Cewu
author_facet Bian, Siyuan
Li, Jiefeng
Tang, Jiasheng
Lu, Cewu
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2403_01345
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ShapeBoost: Boosting Human Shape Estimation with Part-Based Parameterization and Clothing-Preserving Augmentation
Bian, Siyuan
Li, Jiefeng
Tang, Jiasheng
Lu, Cewu
Computer Vision and Pattern Recognition
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.
title ShapeBoost: Boosting Human Shape Estimation with Part-Based Parameterization and Clothing-Preserving Augmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.01345