Abstract | ||
---|---|---|
Image virtual try-on aims to fit a garment image (target clothes) to a person image. Prior methods are heavily based on human parsing. However, slightly-wrong segmentation results would lead to unrealistic try-on images with large artifacts. A recent pioneering work employed knowledge distillation to reduce the dependency of human parsing, where the try-on images produced by a parser-based method are used as supervisions to train a "student" network without relying on segmentation, making the student mimic the try-on ability of the parser-based model. However; the image quality of the student is bounded by the parser-based model. To address this problem, we propose a novel approach, "teacher-tutor-student" knowledge distillation, which is able to produce highly photo-realistic images without human parsing, possessing several appealing advantages compared to prior arts. (1) Unlike existing work, our approach treats the fake images produced by the parser-based method as "tutor knowledge", where the artifacts can be corrected by real "teacher knowledge", which is extracted from the real person images in a self-supervised way. (2) Other than using real images as supervisions, we formulate knowledge distillation in the try-on problem as distilling the appearance flows between the person image and the garment image, enabling us to find accurate dense correspondences between them to produce high-quality results. (3) Extensive evaluations show large superiority of our method (see Fig. 1). |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/CVPR46437.2021.00838 | 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 |
DocType | ISSN | Citations |
Conference | 1063-6919 | 2 |
PageRank | References | Authors |
0.36 | 10 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yuying Ge | 1 | 13 | 1.83 |
Yibing Song | 2 | 3 | 0.71 |
Ruimao Zhang | 3 | 325 | 18.86 |
Chongjian Ge | 4 | 3 | 0.71 |
Wei Liu | 5 | 4041 | 204.19 |
Ping Luo | 6 | 2540 | 111.68 |