EUVIMEDEUVIMED entdecken
Crossref

RealCustom++: Representing Images as Real Textual Word for Real-Time Customization

Zhendong Mao, Mengqi Huang, Fei Ding, Mingcong Liu, Qian He, Yongdong Zhang

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-02 · 48 (2) · 2078-2095

DOI: 10.1109/tpami.2025.3623025 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-02. Verfasst von Zhendong Mao und 5 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 70 Literaturangaben. Gefördert von: Artificial Intelligence National Science and Technology Major Project, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Text-to-image customization aims to generate images that align with both the given text and the subject in the given image. Existing works follow the pseudo-word paradigm, which represents the subject as a non-existent pseudo word and combines it with other text to generate images. However, the pseudo word inherently conflicts and entangles with other real words, resulting in a dual-optimum paradox between the subject similarity and text controllability. To address this, we propose RealCustom++, a novel real-word paradigm that represents the subject with a non-conflicting real word to generate a coherent guidance image and corresponding subject mask, there by disentangling the influence scopes of the text and subject for simultaneous optimization. Specifically, RealCustom++ introduces a train-inference decoupled framework: (1) during training, it learns a general alignment between visual conditions and all real text words; and (2) during inference, a dual-branch architecture is employed, where the Guidance Branch produces the subject guidance mask, and the Generation Branch utilizes this mask to customize the generation of the specific real word exclusively within subject-relevant regions. Extensive experiments validate RealCustom++s superior performance, which improves controllability by 7.48%, similarity by 3.04% and quality by 76.43% simultaneously. Moreover, RealCustom++ further improves controllability by 4.6% and multi-subject similarity by 6.34% for multisubject customization.

Förderung

  • Artificial Intelligence National Science and Technology Major Project
  • National Natural Science Foundation of China

Zitieren

APA

Mao, Z., Huang, M., Ding, F., Liu, M., He, Q., & Zhang, Y. (2026). RealCustom++: Representing Images as Real Textual Word for Real-Time Customization. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(2), 2078-2095. https://doi.org/10.1109/tpami.2025.3623025

Vancouver

Mao Z, Huang M, Ding F, Liu M, He Q, Zhang Y. RealCustom++: Representing Images as Real Textual Word for Real-Time Customization. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(2):2078-2095. doi:10.1109/tpami.2025.3623025

BibTeX
@article{Mao2026,
  author = {Mao, Zhendong and Huang, Mengqi and Ding, Fei and Liu, Mingcong and He, Qian and Zhang, Yongdong},
  title = {RealCustom++: Representing Images as Real Textual Word for Real-Time Customization},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2026},
  volume = {48},
  number = {2},
  pages = {2078--2095},
  doi = {10.1109/tpami.2025.3623025}
}
Kostenlos starten →