# Self-Supervised Image Restoration with Blurry and Noisy Pairs Source: [Self-Supervised Image Restoration with Blurry and Noisy Pairs]() Collection index: [llms.txt]() Data updated: 2026-01-04T05:22:36.667Z Authors: Zhilu Zhang, Rongjian Xu, Ming Liu, Zifei Yan, Wangmeng Zuo Published: 2022-11-14T12:57:41.000Z ## Abstract When taking photos under an environment with insufficient light, the exposure time and the sensor gain usually require to be carefully chosen to obtain images with satisfying visual quality. For example, the images with high ISO usually have inescapable noise, while the long-exposure ones may be blurry due to camera shake or object motion. Existing solutions generally suggest to seek a balance between noise and blur, and learn denoising or deblurring models under either full- or self-supervision. However, the real-world training pairs are difficult to collect, and the self-supervised methods merely rely on blurry or noisy images are limited in performance. In this work, we tackle this problem by jointly leveraging the short-exposure noisy image and the long-exposure blurry image for better image restoration. Such setting is practically feasible due to that short-exposure and long-exposure images can be either acquired by two individual cameras or synthesized by a long burst of images. Moreover, the short-exposure images are hardly blurry, and the long-exposure ones have negligible noise. Their complementarity makes it feasible to learn restoration model in a self-supervised manner. Specifically, the noisy images can be used as the supervision information for deblurring, while the sharp areas in the blurry images can be utilized as the auxiliary supervision information for self-supervised denoising. By learning in a collaborative manner, the deblurring and denoising tasks in our method can benefit each other. Experiments on synthetic and real-world images show the effectiveness and practicality of the proposed method. Codes are available at https://github.com/cszhilu1998/SelfIR. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Image Restoration on Real-World Images raw-RGB (test)](): Image Restoration; Real-World Images raw-RGB (test); NIQE: 5.48. - [Image Restoration on sRGB (Gaussian noise σ ∈ \[5/255, 50/255\]) synthetic (test)](): Image Restoration; sRGB (Gaussian noise σ ∈ \[5/255, 50/255\]) synthetic (test); PSNR: 35.74. - [Image Restoration on sRGB Synthetic (Poisson noise λ=5-50) (test)](): Image Restoration; sRGB (Poisson noise λ ∈ \[5, 50\]) synthetic (test); PSNR: 34.27. - [Image Restoration on Sensor Noise Synthetic raw-RGB (test)](): Image Restoration; Sensor Noise Synthetic raw-RGB (test); PSNR: 34.51. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()