哈尔滨工程大学学报2026，Vol.47Issue(5)：1117-1126,10.DOI:10.11990/jheu.202508030
条件扩散模型驱动的两阶段近红外图像着色方法
A two-stage near-infrared image colorization method driven by a conditional diffusion model
摘要
Abstract
Existing near-infrared(NIR)image colorization methods often suffer from luminance-chrominance confu-sion,texture blurring,and structural artifacts in the generated results.To address these issues,this paper proposes a dual-stage learning framework.In the first stage,a conditional diffusion model is employed to map NIR images into an intermediate grayscale domain that is aligned with the grayscale distribution of target visible-light(VIS)color im-ages while preserving high-frequency details.In the second stage,a mature pre-trained grayscale image colorization network is reused to colorize the predictions from the first stage,enabling high-fidelity color image reconstruction.This strategy effectively decouples the luminance and texture mapping process from the color reconstruction process,significantly reducing the dependence on large-scale paired NIR and VIS color image samples.Experimental results on the public dataset demonstrate that the proposed dual-stage learning framework achieves significant advantages in perceptual quality-related metrics,with the Fréchet distance and perceptual similarity metrics reaching 36.03 and 0.369 6,respectively,outperforming the compared methods,while maintaining comparable performance to state-of-the-art approaches in structure fidelity-related metrics.subjective visual comparisons indicate that the proposed method produces better color consistency and texture detail preservation.关键词
深度学习/图像着色/图像重构/近红外光/可见光/条件扩散模型/图像转换/病态问题Key words
deep learning/image colorization/image reconstruction/near-infrared light/visible light/condi-tional diffusion model/image translation/ill-posed problem分类
信息技术与安全科学引用本文复制引用
唐林瑞泽,刘澍民,陈捷..条件扩散模型驱动的两阶段近红外图像着色方法[J].哈尔滨工程大学学报,2026,47(5):1117-1126,10.基金项目
中央高校基本科研基金项目(G2023KY05108) （G2023KY05108）
国家自然科学基金青年项目(62201470). （62201470）
