File Download
There are no files associated with this item.
Supplementary
-
Citations:
- Appears in Collections:
Conference Paper: Parser-Free Virtual Try-On via Distilling Appearance Flows
Title | Parser-Free Virtual Try-On via Distilling Appearance Flows |
---|---|
Authors | |
Issue Date | 2021 |
Citation | Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Virtual Conference, 19-25 June 2021, p. 8485-8493 How to Cite? |
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).
|
Description | Paper Session Six: Paper ID 1993 |
Persistent Identifier | http://hdl.handle.net/10722/301430 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Ge, Y | - |
dc.contributor.author | Song, Y | - |
dc.contributor.author | Zhang, R | - |
dc.contributor.author | Ge, C | - |
dc.contributor.author | Liu, W | - |
dc.contributor.author | Luo, P | - |
dc.date.accessioned | 2021-07-27T08:10:57Z | - |
dc.date.available | 2021-07-27T08:10:57Z | - |
dc.date.issued | 2021 | - |
dc.identifier.citation | Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Virtual Conference, 19-25 June 2021, p. 8485-8493 | - |
dc.identifier.uri | http://hdl.handle.net/10722/301430 | - |
dc.description | Paper Session Six: Paper ID 1993 | - |
dc.description.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). | - |
dc.language | eng | - |
dc.relation.ispartof | IEEE Computer Vision and Pattern Recognition (CVPR) Proceedings | - |
dc.title | Parser-Free Virtual Try-On via Distilling Appearance Flows | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Luo, P: pluo@hku.hk | - |
dc.identifier.authority | Luo, P=rp02575 | - |
dc.identifier.hkuros | 323752 | - |
dc.identifier.spage | 8485 | - |
dc.identifier.epage | 8493 | - |