VITON: An Image-Based Virtual Try-on Network
- 1 June 2018
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 7543-7552
- https://doi.org/10.1109/cvpr.2018.00787
Abstract
We present an image-based VIirtual Try-On Network (VITON) without using 3D information in any form, which seamlessly transfers a desired clothing item onto the corresponding region of a person using a coarse-to-fine strategy. Conditioned upon a new clothing-agnostic yet descriptive person representation, our framework first generates a coarse synthesized image with the target clothing item overlaid on that same person in the same pose. We further enhance the initial blurry clothing area with a refinement network. The network is trained to learn how much detail to utilize from the target clothing item, and where to apply to the person in order to synthesize a photo-realistic image in which the target item deforms naturally with clear visual patterns. Experiments on our newly collected Zalando dataset demonstrate its promise in the image-based virtual try-on task over state-of-the-art generative models.Keywords
This publication has 32 references indexed in Scilit:
- Learning Visual Clothing Style with Heterogeneous Dyadic Co-OccurrencesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Where to Buy It: Matching Street Clothing Photos in Online ShopsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Effective face frontalization in unconstrained imagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Learning to generate chairs with convolutional neural networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Virtual Fitting by Single-Shot Body Shape EstimationPublished by Hometrica Consulting ,2014
- Paper Doll Parsing: Retrieving Similar Styles to Parse Clothing ItemsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Street-to-shopPublished by Association for Computing Machinery (ACM) ,2012
- DRAPEACM Transactions on Graphics, 2012
- WhittleSearch: Image search with relative attribute feedbackPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2012
- Shape matching and object recognition using shape contextsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2002