FashionComposer: Compositional Fashion Image Generation

Furkejuvvon:
Bibliográfalaš dieđut
Publikašuvnnas:arXiv.org (Dec 19, 2024), p. n/a
Váldodahkki: Ji, Sihui
Eará dahkkit: Wang, Yiyang, Chen, Xi, Xu, Xiaogang, Luo, Hao, Zhao, Hengshuang
Almmustuhtton:
Cornell University Library, arXiv.org
Fáttát:
Liŋkkat:Citation/Abstract
Full text outside of ProQuest
Fáddágilkorat: Lasit fáddágilkoriid
Eai fáddágilkorat, Lasit vuosttaš fáddágilkora!

MARC

LEADER 00000nab a2200000uu 4500
001 3147567236
003 UK-CbPIL
022 |a 2331-8422 
035 |a 3147567236 
045 0 |b d20241219 
100 1 |a Ji, Sihui 
245 1 |a FashionComposer: Compositional Fashion Image Generation 
260 |b Cornell University Library, arXiv.org  |c Dec 19, 2024 
513 |a Working Paper 
520 3 |a We present FashionComposer for compositional fashion image generation. Unlike previous methods, FashionComposer is highly flexible. It takes multi-modal input (i.e., text prompt, parametric human model, garment image, and face image) and supports personalizing the appearance, pose, and figure of the human and assigning multiple garments in one pass. To achieve this, we first develop a universal framework capable of handling diverse input modalities. We construct scaled training data to enhance the model's robust compositional capabilities. To accommodate multiple reference images (garments and faces) seamlessly, we organize these references in a single image as an "asset library" and employ a reference UNet to extract appearance features. To inject the appearance features into the correct pixels in the generated result, we propose subject-binding attention. It binds the appearance features from different "assets" with the corresponding text features. In this way, the model could understand each asset according to their semantics, supporting arbitrary numbers and types of reference images. As a comprehensive solution, FashionComposer also supports many other applications like human album generation, diverse virtual try-on tasks, etc. 
653 |a Feature extraction 
653 |a Semantics 
653 |a Garments 
653 |a Image processing 
700 1 |a Wang, Yiyang 
700 1 |a Chen, Xi 
700 1 |a Xu, Xiaogang 
700 1 |a Luo, Hao 
700 1 |a Zhao, Hengshuang 
773 0 |t arXiv.org  |g (Dec 19, 2024), p. n/a 
786 0 |d ProQuest  |t Engineering Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3147567236/abstract/embedded/ZKJTFFSVAI7CB62C?source=fedsrch 
856 4 0 |3 Full text outside of ProQuest  |u http://arxiv.org/abs/2412.14168