AnyFit: Controllable Virtual Try-on for Any Combination of Attire Across Any Scenario
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911891204341760 |
|---|---|
| author | Li, Yuhan Zhou, Hao Shang, Wenxiang Lin, Ran Chen, Xuanhong Ni, Bingbing |
| author_facet | Li, Yuhan Zhou, Hao Shang, Wenxiang Lin, Ran Chen, Xuanhong Ni, Bingbing |
| contents | While image-based virtual try-on has made significant strides, emerging approaches still fall short of delivering high-fidelity and robust fitting images across various scenarios, as their models suffer from issues of ill-fitted garment styles and quality degrading during the training process, not to mention the lack of support for various combinations of attire. Therefore, we first propose a lightweight, scalable, operator known as Hydra Block for attire combinations. This is achieved through a parallel attention mechanism that facilitates the feature injection of multiple garments from conditionally encoded branches into the main network. Secondly, to significantly enhance the model's robustness and expressiveness in real-world scenarios, we evolve its potential across diverse settings by synthesizing the residuals of multiple models, as well as implementing a mask region boost strategy to overcome the instability caused by information leakage in existing models. Equipped with the above design, AnyFit surpasses all baselines on high-resolution benchmarks and real-world data by a large gap, excelling in producing well-fitting garments replete with photorealistic and rich details. Furthermore, AnyFit's impressive performance on high-fidelity virtual try-ons in any scenario from any image, paves a new path for future research within the fashion community. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_18172 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | AnyFit: Controllable Virtual Try-on for Any Combination of Attire Across Any Scenario Li, Yuhan Zhou, Hao Shang, Wenxiang Lin, Ran Chen, Xuanhong Ni, Bingbing Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning While image-based virtual try-on has made significant strides, emerging approaches still fall short of delivering high-fidelity and robust fitting images across various scenarios, as their models suffer from issues of ill-fitted garment styles and quality degrading during the training process, not to mention the lack of support for various combinations of attire. Therefore, we first propose a lightweight, scalable, operator known as Hydra Block for attire combinations. This is achieved through a parallel attention mechanism that facilitates the feature injection of multiple garments from conditionally encoded branches into the main network. Secondly, to significantly enhance the model's robustness and expressiveness in real-world scenarios, we evolve its potential across diverse settings by synthesizing the residuals of multiple models, as well as implementing a mask region boost strategy to overcome the instability caused by information leakage in existing models. Equipped with the above design, AnyFit surpasses all baselines on high-resolution benchmarks and real-world data by a large gap, excelling in producing well-fitting garments replete with photorealistic and rich details. Furthermore, AnyFit's impressive performance on high-fidelity virtual try-ons in any scenario from any image, paves a new path for future research within the fashion community. |
| title | AnyFit: Controllable Virtual Try-on for Any Combination of Attire Across Any Scenario |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2405.18172 |