SMixNet: Style mixture network for exemplar-based image translation

Zhang, Jinsong, Lai, YuKun ORCID: https://orcid.org/0000-0002-2094-5680, Xiao, Hongjiang and Li, Kun 2026. SMixNet: Style mixture network for exemplar-based image translation. Computational Visual Media 10.26599/CVM.2025.9450458

PDF - Published Version Available under License Creative Commons Attribution. Download (0B)

Abstract

Exemplar-based image translation, which aims to transfer the style of an exemplar image to an input semantic image, is challenging and important in many applications. Most current methods build coarse correspondences and overlook extracting faithful style information from the exemplar image, leading to unsatisfactory results with style inconsistent with the exemplar image. In this paper, we propose a novel and efficient style mixture block to extract faithful style information and build reliable correspondences progressively. Specifically, instead of modeling explicit correspondences, we extract faithful style descriptors by considering global information about the exemplar features. Then, we generate coefficients for these style descriptors by modeling the interaction between the exemplar image and the input image, and efficiently compose these descriptors using the coefficients. The efficiency of the style mixture block allows a multi-scale architecture to extract and transform style descriptors at different resolutions, deforming the features of the exemplar image and refining the correspondences progressively. Experimental results on several datasets show that our SMixNet outperforms the current state-of-the-art, and is faster. Code is available for research purposes at https://github.com/Zhangjinso/SMixNet.

Item Type:	Article
Date Type:	Published Online
Status:	In Press
Schools:	Schools > Computer Science & Informatics
Publisher:	Tsinghua University Press
ISSN:	2096-0662
Date of First Compliant Deposit:	24 March 2026
Date of Acceptance:	19 August 2024
Last Modified:	24 Mar 2026 17:30
URI:	https://orca.cardiff.ac.uk/id/eprint/185968

Actions (repository staff only)

Edit Item