SiCo: An Interactive Size-Controllable Virtual Try-On Approach for Informed Decision-Making

2024-08-05

AI Summary

Existing virtual try-on (VTO) systems rely on fixed garment sizes, lacking size adjustability and personalized fit assessment—leading to inaccurate size selection and high e-commerce return rates. To address this, we propose the first size-controllable interactive virtual try-on paradigm: given a user’s self-captured image, our system performs human parsing, parametric garment modeling, and deformable rendering to synthesize realistic multi-size garment fits on the user’s unique body geometry in real time, with interactive size adjustment. This end-to-end framework uniquely unifies size reasoning, body-aware adaptation, and user-centered decision support. A user study demonstrates significant improvements in size judgment accuracy (+32.7%) and try-on confidence; real-world shopping trials confirm reduced return rates. Our work bridges a critical gap in VTO research and practice by introducing intelligent, user-adaptive size recommendation—establishing a new benchmark for personalized fit simulation.

Technology Category

• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Humans and AI: Game Design — Virtual Humans, NPCs and Autonomous Characters
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• User Modeling, Personalization and Recommendation: Practical large-scale studies of user experience
• Systems and Infrastructure for Web, Mobile and WoT: Virtualization and resource management in Web systems and infrastructures
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

Virtual try-on (VTO) applications aim to replicate the in-store shopping experience and enhance online shopping by enabling users to interact with garments. However, many existing tools adopt a one-size-fits-all approach when visualizing clothing items. This approach limits user interaction with garments, particularly regarding size and fit adjustments, and fails to provide direct insights for size recommendations. As a result, these limitations contribute to high return rates in online shopping. To address this, we introduce SiCo, a new online VTO system that allows users to upload images of themselves and interact with garments by visualizing how different sizes would fit their bodies. Our user study demonstrates that our approach significantly improves users' ability to assess how outfits will appear on their bodies and increases their confidence in selecting clothing sizes that align with their preferences. Based on our evaluation, we believe that SiCo has the potential to reduce return rates and transform the online clothing shopping experience.

Problem

• Existing VTO tools lack size and fit customization
• Current methods fail to provide accurate size recommendations
• High return rates due to poor virtual try-on experiences

Innovation

• Interactive size-controllable virtual try-on system
• User-uploaded images for personalized garment visualization
• Real-time fit adjustment for confident size selection