About

Image Restoration is a family of inverse problems for obtaining a high quality image from a corrupted input image. Corruption may occur due to the image-capture process (e.g., noise, lens blur), post-processing (e.g., JPEG compression), or photography in non-ideal conditions (e.g., haze, motion blur).

Source: Blind Image Restoration without Prior Knowledge

Benchmarks

You can find evaluation results in the subtasks. You can also submitting evaluation metrics for this task.

Subtasks

Datasets

Latest papers without code

Perceptual Image Restoration with High-Quality Priori and Degradation Learning

4 Mar 2021

We show that our model performs well in measuring the similarity between restored and degraded images.

IMAGE RESTORATION NO-REFERENCE IMAGE QUALITY ASSESSMENT

Deblurring Processor for Motion-Blurred Faces Based on Generative Adversarial Networks

3 Mar 2021

Then we conducted a motion blur image generation experiment on some general facial data set, and used the pairs of blurred and sharp face image data to perform the training and testing experiments of the processor GAN, and gave some visual displays.

DEBLURRING FACE DETECTION FACE RECOGNITION IMAGE GENERATION IMAGE RESTORATION

Feature-Align Network and Knowledge Distillation for Efficient Denoising

2 Mar 2021

Deep learning-based RAW image denoising is a quintessential problem in image restoration.

IMAGE DENOISING IMAGE RESTORATION KNOWLEDGE DISTILLATION

Deep Unrolled Network for Video Super-Resolution

23 Feb 2021

Yet, they fail to incorporate some knowledge about the image formation model, which limits their flexibility.

IMAGE RESTORATION VIDEO SUPER-RESOLUTION

A GAN-Based Input-Size Flexibility Model for Single Image Dehazing

19 Feb 2021

Based on the atmospheric scattering model, we design a novel model to directly generate the haze-free image.

IMAGE DEHAZING IMAGE RESTORATION IMAGE-TO-IMAGE TRANSLATION SINGLE IMAGE DEHAZING

Learning local regularization for variational image restoration

11 Feb 2021

In this work, we propose a framework to learn a local regularization model for solving general image restoration problems.

DEBLURRING DENOISING IMAGE RESTORATION

Learning to Enhance Visual Quality via Hyperspectral Domain Mapping

10 Feb 2021

We incorporate a self-supervision and a spectral profile regularization network to infer a plausible HSI from an RGB image.

IMAGE RESTORATION

Image Restoration by Deep Projected GSURE

4 Feb 2021

In the first one, where no explicit prior is used, we show that the proposed approach outperforms other internal learning methods, such as DIP.

DEBLURRING IMAGE RESTORATION SUPER-RESOLUTION