Learning the Loss Functions in a Discriminative Space for Video Restoration

03/20/2020
by   Younghyun Jo, et al.
16

With more advanced deep network architectures and learning schemes such as GANs, the performance of video restoration algorithms has greatly improved recently. Meanwhile, the loss functions for optimizing deep neural networks remain relatively unchanged. To this end, we propose a new framework for building effective loss functions by learning a discriminative space specific to a video restoration task. Our framework is similar to GANs in that we iteratively train two networks - a generator and a loss network. The generator learns to restore videos in a supervised fashion, by following ground truth features through the feature matching in the discriminative space learned by the loss network. In addition, we also introduce a new relation loss in order to maintain the temporal consistency in output videos. Experiments on video superresolution and deblurring show that our method generates visually more pleasing videos with better quantitative perceptual metric values than the other state-of-the-art methods.

READ FULL TEXT

page 10

page 14

page 16

page 18

page 19

page 20

page 21

research
06/01/2021

Fourier Space Losses for Efficient Perceptual Image Super-Resolution

Many super-resolution (SR) models are optimized for high performance onl...
research
03/09/2021

Knowledge Evolution in Neural Networks

Deep learning relies on the availability of a large corpus of data (labe...
research
09/19/2022

Learning Symbolic Model-Agnostic Loss Functions via Meta-Learning

In this paper, we develop upon the emerging topic of loss function learn...
research
03/01/2018

Exploiting the Potential of Standard Convolutional Autoencoders for Image Restoration by Evolutionary Search

Researchers have applied deep neural networks to image restoration tasks...
research
03/26/2021

Training a Better Loss Function for Image Restoration

Central to the application of neural networks in image restoration probl...
research
12/08/2020

Overcomplete Representations Against Adversarial Videos

Adversarial robustness of deep neural networks is an extensively studied...
research
06/22/2023

Restoration of the JPEG Maximum Lossy Compressed Face Images with Hourglass Block based on Early Stopping Discriminator

When a JPEG image is compressed using the loss compression method with a...

Please sign up or login with your details

Forgot password? Click here to reset