2026-09-22T03:25:08Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/122215 2024-03-02 col_2142_5131 col_2142_10761 com_2142_5130 com_2142_10755 com_2142_234

Forsyth, David Alexander Forsyth, David Alexander Lazebnik, Svetlana Schwing, Alexander Gerhard Farhadi, Ali 2023-12 application/pdf en text Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2025-12-01 The student, Kedan Li, accepted the attached license on 2023-11-11 at 08:15. The student, Kedan Li, submitted this Dissertation for approval on 2023-11-11 at 08:21. This Dissertation was approved for publication on 2023-11-20 at 09:52. DSpace SAF Submission Ingestion Package generated from Vireo submission #19905 on 2024-03-01 at 13:48:06 A scalable system for virtual dressing Li, Kedan Virtual Try-on (vton) Systems Image Synthesis Warping Computer Vision Fashion 2023-11-20 Styling plays a crucial role in the fashion industry, and for years, there has been a search for a way to virtually visualize outfits on a person accurately and instantly. Virtual try-on (VTON) systems offer this capability, but several technical challenges have limited their widespread commercial adoption. These challenges fall into three main categories: (1) quality - generating an appealing and accurate try-on image; (2) intractability - handling outfit combinations, instant feedback, styling variations, model selection, etc.; (3) practicality - addressing product catalog coverage, logistics, and costs. In this thesis, we thoroughly examine the key components of virtual try-on systems and develop an effective solution to address these challenges. Our approach introduces a multi-garment VTON method that accurately captures garment attributes and provides instant responses. We also devise a technique that adjusts garment draping (e.g., tucked vs. untucked) while maintaining the garment's identity, allowing for the generation of rendering policies that dictate outfit styling and layering. Moreover, we suggest various enhancements to improve detail preservation and overall quality. Our proposed VTON system not only achieves remarkable results on benchmark datasets but has also been successfully implemented by top fashion retailers in the industry. Text eng https://hdl.handle.net/2142/122215 Copyright 2023 Kedan Li Ph.D. Dissertation Computer Science University of Illinois at Urbana-Champaign Computer Science