Template-Free Try-on Image Synthesis via Semantic-guided Optimization
This work aims to improve the realism and user-friendliness of virtual try-on systems for consumers by addressing issues like user-specified poses and problematic cases such as facial details and clothing wrinkles; it appears to be an incremental improvement.
This paper addresses the virtual try-on task by proposing a template-free try-on image synthesis (TF-TIS) network that first synthesizes a target pose based on in-shop clothing and then generates a try-on image. The method reportedly outperforms state-of-the-art approaches, particularly in challenging scenarios.
The virtual try-on task is so attractive that it has drawn considerable attention in the field of computer vision. However, presenting the three-dimensional (3D) physical characteristic (e.g., pleat and shadow) based on a 2D image is very challenging. Although there have been several previous studies on 2D-based virtual try-on work, most 1) required user-specified target poses that are not user-friendly and may not be the best for the target clothing, and 2) failed to address some problematic cases, including facial details, clothing wrinkles and body occlusions. To address these two challenges, in this paper, we propose an innovative template-free try-on image synthesis (TF-TIS) network. The TF-TIS first synthesizes the target pose according to the user-specified in-shop clothing. Afterward, given an in-shop clothing image, a user image, and a synthesized pose, we propose a novel model for synthesizing a human try-on image with the target clothing in the best fitting pose. The qualitative and quantitative experiments both indicate that the proposed TF-TIS outperforms the state-of-the-art methods, especially for difficult cases.