ALiSNet: Accurate and Lightweight Human Segmentation Network for Fashion E-Commerce

Amrollah Seifoddini, Koen Vernooij, Timon Künzle, Alessandro Canopoli, Malte Alf, Anna Volokitin, Reza Shirvany

2023

Abstract

Accurately estimating human body shape from photos can enable innovative applications in fashion, from mass customization, to size and fit recommendations and virtual try-on. Body silhouettes calculated from user pictures are effective representations of the body shape for downstream tasks. Smartphones provide a convenient way for users to capture images of their body, and on-device image processing allows predicting body segmentation while protecting users’ privacy. Existing off-the-shelf methods for human segmentation are closed source and cannot be specialized for our application of body shape and measurement estimation. Therefore, we create a new segmentation model by simplifying Semantic FPN with PointRend, an existing accurate model. We finetune this model on a high-quality dataset of humans in a restricted set of poses relevant for our application. We obtain our final model, ALiSNet, with a size of 4MB and 97.6 ± 1.0% mIoU, compared to Apple Person Segmentation, which has an accuracy of 94.4 ± 5.7% mIoU on our dataset.

Paper Citation

in Harvard Style

Seifoddini A., Vernooij K., Künzle T., Canopoli A., Alf M., Volokitin A. and Shirvany R. (2023). ALiSNet: Accurate and Lightweight Human Segmentation Network for Fashion E-Commerce. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 4: VISAPP; ISBN 978-989-758-634-7, SciTePress, pages 746-754. DOI: 10.5220/0011670400003417

in Bibtex Style

@conference{visapp23,
author={Amrollah Seifoddini and Koen Vernooij and Timon Künzle and Alessandro Canopoli and Malte Alf and Anna Volokitin and Reza Shirvany},
title={ALiSNet: Accurate and Lightweight Human Segmentation Network for Fashion E-Commerce},
booktitle={Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 4: VISAPP},
year={2023},
pages={746-754},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011670400003417},
isbn={978-989-758-634-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 4: VISAPP
TI - ALiSNet: Accurate and Lightweight Human Segmentation Network for Fashion E-Commerce
SN - 978-989-758-634-7
AU - Seifoddini A.
AU - Vernooij K.
AU - Künzle T.
AU - Canopoli A.
AU - Alf M.
AU - Volokitin A.
AU - Shirvany R.
PY - 2023
SP - 746
EP - 754
DO - 10.5220/0011670400003417
PB - SciTePress