DeepAI AI Chat
Log In Sign Up

Learning the Loss Functions in a Discriminative Space for Video Restoration

by   Younghyun Jo, et al.

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.


page 10

page 14

page 16

page 18

page 19

page 20

page 21


Fourier Space Losses for Efficient Perceptual Image Super-Resolution

Many super-resolution (SR) models are optimized for high performance onl...

Knowledge Evolution in Neural Networks

Deep learning relies on the availability of a large corpus of data (labe...

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

Researchers have applied deep neural networks to image restoration tasks...

Training a Better Loss Function for Image Restoration

Central to the application of neural networks in image restoration probl...

Attention Transfer from Web Images for Video Recognition

Training deep learning based video classifiers for action recognition re...

Overcomplete Representations Against Adversarial Videos

Adversarial robustness of deep neural networks is an extensively studied...