UTMCR: 3U‐Net Transformer With Multi‐Contrastive Regularization for Single Image Dehazing

• Published in: Computer animation and virtual worlds Vol. 36; no. 3
• Main Authors: Xu, HangBin, Zou, ChangJun, Lin, ChuChao
• Format: Journal Article
• Language: English
• Published: Hoboken, USA John Wiley & Sons, Inc 01.05.2025; Wiley Subscription Services, Inc
• Subjects: Artificial neural networks; contrastive regularization; image dehazing; Modelling; Modules; Regularization; Regularization methods; Swin Transformer; U‐Net
• DOI: 10.1002/cav.70029
• ISSN: 1546-4261

ABSTRACT Convolutional neural networks have a long history of development in single‐width dehazing tasks, but have gradually been dominated by the Transformer framework due to their insufficient global modeling capability and large number of parameters. However, the existing Transformer network structure adopts a single U‐Net structure, which is insufficient in multi‐level and multi‐scale feature fusion and modeling capability. Therefore, we propose an end‐to‐end dehazing network (UTMCR‐Net). The network consists of two parts: (1) UT module, which connects three U‐Net networks in series, where the backbone is replaced by the Dehazeformer block. By connecting three U‐Net networks in series, we can improve the image global modeling capability and capture multi‐scale information at different levels to achieve multi‐level and multi‐scale feature fusion. (2) MCR module, which improves the original contrastive regularization method by splitting the results of the UT module into four equal blocks, which are then compared and learned by using the contrast regularization method, respectively. Specifically, we use three U‐Net networks to enhance the global modeling capability of UTMCR as well as the multi‐scale feature fusion capability. The image dehazing ability is further enhanced using the MCR module. Experimental results show that our method achieves better results on most datasets. UTMCR proposes a single image dehazing method combining 3U‐Net and Transformer, enhanced by Multi‐Contrastive Regularization (MCR) to improve feature discriminability while preserving local details and global dehazing performance. The framework employs a multi‐scale U‐shaped architecture for progressive restoration and introduces contrastive learning to optimize feature distributions between clear and hazy images, significantly improving reconstruction quality in complex hazy scenes.