Importing Diffusion and Re-Designed Backward Process for Image De-Raining

• Published in: Sensors (Basel, Switzerland) Vol. 24; no. 12; p. 3715
• Main Authors: Lin, Jhe-Wei, Lee, Cheng-Hsuan, Su, Tang-Wei, Chang, Che-Cheng
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 07.06.2024; MDPI
• Subjects: de-rained; Deep learning; diffusion model; Diffusion models; feature extraction; image process; Machine learning; Natural language processing; Rain; Realism; diffusion model; de-rained; feature extraction; image process
• DOI: 10.3390/s24123715
• ISSN: 1424-8220

In recent years, with the increasing demand for high-quality images in various fields, more and more attention has been focused on noise removal techniques for image processing. The effective elimination of unwanted noise plays a crucial role in improving image quality. To meet this challenge, many noise removal methods have been proposed, among which the diffusion model has become one of the focuses of many researchers. In order to make the restored image closer to the real image and retain more features of the image, this paper proposes a DIR-SDE method with reference to the diffusion models of IR-SDE and IDM, which improve the feature retention of the image in the de-raining process, and then improve the realism of the image for the image de-raining task. In this study, IR-SDE was used as the base structure of the diffusion model, IR-SDE was improved, and DINO-ViT was combined to enhance the image features. During the diffusion process, the image features were extracted using DINO-ViT, and these features were fused with the original images to enhance the learning effect of the model. The model was also trained and validated with the Rain100H dataset. Compared with the IR-SDE method, it improved 0.003 in the SSIM, 0.003 in the LPIPS, and 1.23 in the FID. The experimental results show that the diffusion model proposed in this study can effectively improve the image restoration performance.