Shape of You: Precise 3D shape estimations for diverse body types

TL;DR

This paper introduces Shape of You (SoY), a novel approach with new loss functions and test-time optimization that significantly enhances 3D human shape estimation accuracy across diverse body types for practical applications.

Contribution

We propose two new loss functions and a test-time optimization routine to improve 3D human shape estimation accuracy for diverse body types.

Findings

17.7% improvement over SHAPY on SSP-3D dataset

Enhanced accuracy for diverse human body shapes

Potential for practical fashion industry applications

Abstract

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