Multi-Scale Optimal Transport Transformer for Efficient Exemplar-Based Image Translation
Big Data and Cognitive Computing · 01.04.2026 · 10 (4) · 107
DOI: 10.3390/bdcc10040107 ↗Kurz gefasst
Fachartikel in der Zeitschrift Big Data and Cognitive Computing, online erschienen am 01.04.2026. Verfasst von Jinsong Zhang und 2 weiteren Autor:innen. Die Arbeit nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Exemplar-based image translation generates an output image by transferring appearance from a reference exemplar to a content image. Existing works only consider the local correspondences between two modalities, and ignore the global distributions in each modality, struggling to obtain fine-grained details with efficient computation. In this paper, we propose OTFormer, a multi-scale Optimal Transport transformer for exemplarbased image translation. We formulate cross-modal alignment as a multi-scale optimal transport problem, which progressively provides a globally coherent matching. In addition, we design a lightweight multi-scale fusion block to extract and fuse features efficiently. Experiments on CelebA-HQ and DeepFashion demonstrate that OTFormer improves both image fidelity and style adherence, while reducing model parameters by 62% and achieving faster inference compared with strong baselines. These results highlight OTguided global alignment as an effective and deployable solution for high-fidelity exemplarbased image translation.
Zitieren
APA
Zhang, J., Li, X., & Lin, Y. (2026). Multi-Scale Optimal Transport Transformer for Efficient Exemplar-Based Image Translation. Big Data and Cognitive Computing, 10(4), 107. https://doi.org/10.3390/bdcc10040107
Vancouver
Zhang J, Li X, Lin Y. Multi-Scale Optimal Transport Transformer for Efficient Exemplar-Based Image Translation. Big Data and Cognitive Computing. 2026;10(4):107. doi:10.3390/bdcc10040107
BibTeX
@article{Zhang2026,
author = {Zhang, Jinsong and Li, Xiongzheng and Lin, Yuqin},
title = {Multi-Scale Optimal Transport Transformer for Efficient Exemplar-Based Image Translation},
journal = {Big Data and Cognitive Computing},
year = {2026},
volume = {10},
number = {4},
pages = {107},
doi = {10.3390/bdcc10040107}
}
EUVIMED