Learning the Loss Functions in a Discriminative Space for Video Restoration
This addresses the challenge of improving video quality in restoration tasks like superresolution and deblurring, though it is incremental as it builds on existing GAN-like frameworks.
The paper tackles the problem of designing effective loss functions for video restoration by learning a discriminative space, resulting in visually more pleasing videos with better quantitative perceptual metrics than state-of-the-art methods.
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.