Abstract
Both noise and structure matter in single image super-resolution (SISR). Recent researches have benefited from a generative adversarial network (GAN) that promotes the development of SISR by recovering photo-realistic images. However, noise and structural distortion are detrimental to SISR. In this paper, we focus on eliminating noise and geometric distortion during super-resolving noisy images. It includes a denoising preprocessing module and a structure-keeping branch. At the same time, the advantages of GAN are still used to generate satisfying details. Especially, on the basis of the original SISR, the gradient branch is developed, and the denoising preprocessing module is designed before the SR branch. Denoising preprocessing eliminates noise by learning the noise distribution and utilizing residual-skip. By restoring the high-resolution(HR) gradient maps and combining gradient loss with space loss to guide the parameter optimization, the gradient branch brings additional structural constraints. Experimental results show that we have obtained better Perceptual Index (PI) and Learned Perceptual Image Patch Similarity (LPIPS) performance on the noisy images, and Peak Signal to Noise Ratio(PSNR) and Structure Similarity (SSIM) are equivalent compared with the most reported SR method combined with DNCNN. Taking the Urban100 dataset with noise intensity in 25 as an example, four indexes of the proposed method are respectively 3.6976(PI), 0.1124(LPIPS), 24.652(PSNR) and 0.9481(SSIM). Combined with the performance under different noise intensity and different datasets reflected in box-and-whiskers plots, the values of PI and LPIPS are the best among all comparison methods, and PSNR and SSIM also achieve equivalent effects. Also, the visual results show that the proposed method of enhancing the super-resolving effect of noisy images through structural information and denoising preprocessing(SNS) is not affected by the noise while preserving the geometric structure in SR processing.
Highlights
Image denoising and super-resolution (SR), which aim to reconstruct high-quality images from low-quality observations are fundamental to complex image processing fields such as image Mosaic, AI 2020, 1, 329–341; doi:10.3390/ai1030022 www.mdpi.com/journal/aiAI 2020, 1 resolution images, and the noise makes the input of the mapping deviate from the actual image to be enhanced, thereby affecting the results
Image denoising and super-resolution (SR), which aim to reconstruct high-quality images from low-quality observations are fundamental to complex image processing fields such as image Mosaic, 3D reconstruction, and simultaneous localization and mapping (SLAM)
We introduce edge constraints to reduce the geometric distortion generated in the process of denoising and generative adversarial network (GAN)-based super-resolving
Summary
AI 2020, 1 resolution images, and the noise makes the input of the mapping deviate from the actual image to be enhanced, thereby affecting the results. The images generated by GAN [1] often suffer from structural distortions, resulting in large visual gaps with the original images. Traditional denoising methods can only focus on unique noise types and lose too much information, while the cost of advanced network methods involves complex calculation. With the introduction of structural information, the GAN-based method improves the image structure retention while the noise still affects the consequent. Considering that noise interference and structural distortion often exist together in SR tasks, the image denoising and SR in one task are handled.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
