VITON: An Image-based Virtual Try-on Network
This addresses the need for realistic virtual try-on in e-commerce, though it is incremental as it builds on existing generative models.
The paper tackles the problem of virtual try-on by transferring a clothing item onto a person's image without 3D information, using a coarse-to-fine strategy to generate photo-realistic results with clear patterns and natural deformation, as demonstrated on a new Zalando dataset.
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.