Authors:
Amrollah Seifoddini
1
;
Koen Vernooij
1
;
Timon Künzle
1
;
Alessandro Canopoli
1
;
Malte Alf
1
;
Anna Volokitin
1
and
Reza Shirvany
2
Affiliations:
1
Zalando SE, Switzerland
;
2
Zalando SE, Germany
Keyword(s):
On-Device, Human-Segmentation, Privacy-Preserving, Fashion, e-Commerce.
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.
(More)