# Estimation of 3D Body Shape and Clothing Measurements from Frontal- and Side-view Images

arXiv: https://arxiv.org/abs/2205.14347 · HTML: https://mlsanity.com/paper/2205.14347/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 20 references that are in the map.
- First posted on arXiv 28 May 2022.

## Builds on (most cited first, 7 of 7)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Synthetic Training for Accurate 3D Human Pose and Shape Estimation in the Wild](https://mlsanity.com/paper/2009.10013/) (2020)
- [Anthropometric clothing measurements from 3D body scans](https://mlsanity.com/paper/1911.00694/) (2019)
- [CALVIS: chest, waist and pelvis circumference from 3D human body meshes as ground truth for deep learning](https://mlsanity.com/paper/2003.00834/) (2020)
- [Automatic Estimation of Anthropometric Human Body Measurements](https://mlsanity.com/paper/2112.11992/) (2021)
- [Shape-from-Mask: A Deep Learning Based Human Body Shape Reconstruction from Binary Mask Images](https://mlsanity.com/paper/1806.08485/) (2018)

## Built on by (most cited first, 1 of 1)

- [ClothFit: Cloth-Human-Attribute Guided Virtual Try-On Network Using 3D Simulated Dataset](https://mlsanity.com/paper/2306.13908/) (2023)

## Abstract (arXiv)

The estimation of 3D human body shape and clothing measurements is crucial for virtual try-on and size recommendation problems in the fashion industry but has always been a challenging problem due to several conditions, such as lack of publicly available realistic datasets, ambiguity in multiple camera resolutions, and the undefinable human shape space. Existing works proposed various solutions to these problems but could not succeed in the industry adaptation because of complexity and restrictions. To solve the complexity and challenges, in this paper, we propose a simple yet effective architecture to estimate both shape and measures from frontal- and side-view images. We utilize silhouette segmentation from the two multi-view images and implement an auto-encoder network to learn low-dimensional features from segmented silhouettes. Then, we adopt a kernel-based regularized regression module to estimate the body shape and measurements. The experimental results show that the proposed method provides competitive results on the synthetic dataset, NOMO-3d-400-scans Dataset, and RGB Images of humans captured in different cameras.