Special Topics in Multimodal Fusion
|
App. Res. of Comp. Printed Article
Vol. 43, 2026 No. 11
3266-3272

SiFashion: scene-based outfits generation network based on diffusion models

Liu Yu
Shi Yingjie
Chi Cheng
Liao Yuanhong
School of Artificial Intelligence and Creative Design, Beijing Institute of Fashion Technology, Beijing 100048, China
DOI: 10.19734/j.issn.1001-3695.2026.03.0073

Abstract

In response to the problem that existing generative outfits recommendation systems are difficult to control the dres-sing scenarios, this paper proposed a scene-based outfits generation network called SiFashion, based on the diffusion model. Within the framework of the potential diffusion model, this method introduced the scene conditions and constructed a scene encoder, mapping the discrete scene labels into spatial condition features, and achieving the joint control and generation of scene, personalized history, and compatibility through CFG. At the same time, it constructed a multi-modal outfits dataset named Scene-Outfits based on the Polyvore and iFashion datasets, which integrated information such as compatibility, user personalization details, and outfit scene. This dataset covered four types of outfits scene with significant style differences, including casual, sporty, conference, and trendy, and contained a total of 22 831 outfits pairings, covering 16 types of clothing items such as tops, pants, bags, and shoes. Experimental results show that on the Scene-Outfits dataset, compared with the baseline model, SiFashion maintains similar levels in general generation metrics such as FID, CS, and COMP. However, in expert reviews and large model evaluations, the scene compliance rate of SiFashion is higher than that of the comparison methods, fully demonstrating the effectiveness of this method in generating controlled dressing scenarios.

Foundation Support

北京服装学院研究生教学改革项目(NHFZ20260796)
北京服装学院教学改革项目(ZDJG-2508)
北京服装学院服装智能化定制系统核心技术攻关项目(NHFZ20260254)
北京服装学院研究生高水平拔尖创新人才培育项目(NHFZ20260275)
国家自然科学基金资助项目(62062058)
北京市教育委员会科学研究计划资助项目(KM202210012002)
纺织服装智能化湖北省工程研究中心开放课题(2023HBITF01)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2026.03.0073
Publish at: Application Research of Computers Printed Article, Vol. 43, 2026 No. 11
Section: Special Topics in Multimodal Fusion
Pages: 3266-3272
Serial Number: 1001-3695(2026)11-009-3266-07

Publish History

[2026-11-05] Printed Article

Cite This Article

刘宇, 史英杰, 迟丞, 等. SiFashion:一种基于扩散模型的场景式服装穿搭生成网络 [J]. 计算机应用研究, 2026, 43 (11): 3266-3272. (Liu Yu, Shi Yingjie, Chi Cheng, et al. SiFashion: scene-based outfits generation network based on diffusion models [J]. Application Research of Computers, 2026, 43 (11): 3266-3272. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.

Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2025 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)