EUVIMEDOpdag EUVIMED
Open access · CC BY 4.0

Image Colorization with Residual Attention U-Net

Jun Yang, Donghui Zhang, Fan Wu, Le Yang

Electronics · 2026-04-01 · 15 (7) · 1462

DOI: 10.3390/electronics15071462 ↗

At a glance

Journal article in Electronics, published online on 2026-04-01. Written by Jun Yang and 3 co-authors. 48 references. The full text is freely available (open access, CC BY 4.0). Funded by: National Natural Science Foundation Project of China.

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Image colorization aims to add plausible colors to grayscale images. However, existing methods often suffer from detail loss, dull colors, and unrealistic results. To address these issues, we propose a novel image colorization method based on a residual attention U-Net. First, a shallow feature extraction module with a fusion attention mechanism is designed to capture shallow features. Second, a residual attention U-Net is constructed by integrating a residual attention module into an improved U-Net architecture. Finally, we fuse the extracted shallow features with the shallow attention features within the residual attention U-Net to enhance detail preservation and improve colorization quality. Experimental results on the summer2winter dataset show that our method improves the average PSNR by 1.32 dB and SSIM by 0.0139, while reducing LPIPS by 0.01. Furthermore, our method achieves the best average PSNR and LPIPS on the NCData and COCO-Stuff datasets. Visual results demonstrate that our approach preserves fine details, produces more vibrant colors, and achieves a higher degree of realism and naturalness.

Funding

  • National Natural Science Foundation Project of China

Cite

APA

Yang, J., Zhang, D., Wu, F., & Yang, L. (2026). Image Colorization with Residual Attention U-Net. Electronics, 15(7), 1462. https://doi.org/10.3390/electronics15071462

Vancouver

Yang J, Zhang D, Wu F, Yang L. Image Colorization with Residual Attention U-Net. Electronics. 2026;15(7):1462. doi:10.3390/electronics15071462

BibTeX
@article{Yang2026,
  author = {Yang, Jun and Zhang, Donghui and Wu, Fan and Yang, Le},
  title = {Image Colorization with Residual Attention U-Net},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {7},
  pages = {1462},
  doi = {10.3390/electronics15071462}
}
Start for free →