Sarkar Rohan ; Dave Achal ; Medioni Gerard ; Biggs Benjamin

Abstract

This paper presents Shape of You (SoY), an approach to improve the accuracyof 3D body shape estimation for vision-based clothing recommendation systems.While existing methods have successfully estimated 3D poses, there remains alack of work in precise shape estimation, particularly for diverse humanbodies. To address this gap, we propose two loss functions that can be readilyintegrated into parametric 3D human reconstruction pipelines. Additionally, wepropose a test-time optimization routine that further improves quality. Ourmethod improves over the recent SHAPY method by 17.7% on the challenging SSP-3Ddataset. We consider our work to be a step towards a more accurate 3D shapeestimation system that works reliably on diverse body types and holds promisefor practical applications in the fashion industry.