DeepAI
Log In Sign Up

Training a Better Loss Function for Image Restoration

03/26/2021
by   Aamir Mustafa, et al.
14

Central to the application of neural networks in image restoration problems, such as single image super resolution, is the choice of a loss function that encourages natural and perceptually pleasing results. A popular choice for a loss function is a pre-trained network, such as VGG and LPIPS, which is used as a feature extractor for computing the difference between restored and reference images. However, such an approach has multiple drawbacks: it is computationally expensive, requires regularization and hyper-parameter tuning, and involves a large network trained on an unrelated task. In this work, we explore the question of what makes a good loss function for an image restoration task. First, we observe that a single natural image is sufficient to train a lightweight feature extractor that outperforms state-of-the-art loss functions in single image super resolution, denoising, and JPEG artefact removal. We propose a novel Multi-Scale Discriminative Feature (MDF) loss comprising a series of discriminators, trained to penalize errors introduced by a generator. Second, we show that an effective loss function does not have to be a good predictor of perceived image quality, but instead needs to be specialized in identifying the distortions for a given restoration method.

READ FULL TEXT

page 4

page 6

page 8

page 9

page 10

page 11

page 12

07/22/2017

Single Image Super-Resolution with Dilated Convolution based Multi-Scale Information Learning Inception Module

Traditional works have shown that patches in a natural image tend to red...
02/27/2019

Generative Collaborative Networks for Single Image Super-Resolution

A common issue of deep neural networks-based methods for the problem of ...
01/11/2022

Image quality measurements and denoising using Fourier Ring Correlations

Image quality is a nebulous concept with different meanings to different...
04/19/2019

Feature Forwarding for Efficient Single Image Dehazing

Haze degrades content and obscures information of images, which can nega...
03/20/2020

Learning the Loss Functions in a Discriminative Space for Video Restoration

With more advanced deep network architectures and learning schemes such ...
12/01/2022

Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model

Most existing Image Restoration (IR) models are task-specific, which can...