Joint Learning of Multiple Image Restoration Tasks

07/10/2019
by   Xing Liu, et al.
4

Convolutional neural networks have recently been successfully applied to the problems of restoring clean images from their degraded versions. Most studies have designed and trained a dedicated network for each of many image restoration tasks, such as motion blur removal, rain-streak removal, haze removal, etc. In this paper, we show that a single network having a single input and multiple output branches can solve multiple image restoration tasks. This is made possible by improving the attention mechanism and an internal structure of the basic blocks used in the dual residual networks, which was recently proposed and shown to work well for a number of image restoration tasks by Liu et al. Experimental results show that the proposed approach achieves a new state-of-the-art performance on haze removal (both in PSNR/SSIM) and JPEG artifact removal (in SSIM). To the authors' knowledge, this is the first report of successful multi-task learning on diverse image restoration tasks.

READ FULL TEXT

page 1

page 2

page 5

page 6

page 7

page 9

page 10

page 11

research
08/19/2020

LIRA: Lifelong Image Restoration from Unknown Blended Distortions

Most existing image restoration networks are designed in a disposable wa...
research
03/21/2019

Dual Residual Networks Leveraging the Potential of Paired Operations for Image Restoration

In this paper, we study design of deep neural networks for tasks of imag...
research
10/22/2020

Self-Supervised Shadow Removal

Shadow removal is an important computer vision task aiming at the detect...
research
11/15/2022

Cross-Stitched Multi-task Dual Recursive Networks for Unified Single Image Deraining and Desnowing

We present the Cross-stitched Multi-task Unified Dual Recursive Network ...
research
08/20/2023

WMFormer++: Nested Transformer for Visible Watermark Removal via Implict Joint Learning

Watermarking serves as a widely adopted approach to safeguard media copy...
research
10/09/2020

Deep-Masking Generative Network: A Unified Framework for Background Restoration from Superimposed Images

Restoring the clean background from the superimposed images containing a...
research
05/12/2017

Self-Committee Approach for Image Restoration Problems using Convolutional Neural Network

There have been many discriminative learning methods using convolutional...

Please sign up or login with your details

Forgot password? Click here to reset