POVNet: Image-Based Virtual Try-On Through Accurate Warping and Residual

Kedan Li, Jeffrey Zhang, David Forsyth

Research output: Contribution to journalArticlepeer-review


Virtual dressing room applications help online shoppers visualize outfits. Such a system, to be commercially viable, must satisfy a set of performance criteria. The system must produce high quality images that faithfully preserve garment properties, allow users to mix and match garments of various types and support human models varying in skin tone, hair color, body shape, and so on. This paper describes POVNet, a framework that meets all these requirements (except body shapes variations). Our system uses warping methods together with residual data to preserve garment texture at fine scales and high resolution. Our warping procedure adapts to a wide range of garments and allows swapping in and out of individual garments. A learned rendering procedure using an adversarial loss ensures that fine shading, etc. is accurately reflected. A distance transform representation ensures that hems, cuffs, stripes, and so on are correctly placed. We demonstrate improvements in garment rendering over state of the art resulting from these procedures. We demonstrate that the framework is scalable, responds in real-time, and works robustly with a variety of garment categories. Finally, we demonstrate that using this system as a virtual dressing room interface for fashion e-commerce websites has significantly boosted user-engagement rates.

Original languageEnglish (US)
Pages (from-to)12222-12235
Number of pages14
JournalIEEE transactions on pattern analysis and machine intelligence
Issue number10
StatePublished - Oct 1 2023


  • application
  • generative adversarial networks
  • image generation
  • image in-painting
  • positional encoding
  • Virtual try-on
  • warping

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Computational Theory and Mathematics
  • Artificial Intelligence
  • Applied Mathematics


Dive into the research topics of 'POVNet: Image-Based Virtual Try-On Through Accurate Warping and Residual'. Together they form a unique fingerprint.

Cite this