Discriminative Transfer Learning for General Image Restoration
This addresses the time-consuming and limited training issue for image restoration tasks, offering a more flexible and efficient solution for researchers and practitioners in computer vision.
The paper tackles the problem of separate training for each image restoration task and condition by proposing a discriminative transfer learning method that requires only single-pass training and allows reuse across various problems, achieving efficiency comparable to previous approaches.
Recently, several discriminative learning approaches have been proposed for effective image restoration, achieving convincing trade-off between image quality and computational efficiency. However, these methods require separate training for each restoration task (e.g., denoising, deblurring, demosaicing) and problem condition (e.g., noise level of input images). This makes it time-consuming and difficult to encompass all tasks and conditions during training. In this paper, we propose a discriminative transfer learning method that incorporates formal proximal optimization and discriminative learning for general image restoration. The method requires a single-pass training and allows for reuse across various problems and conditions while achieving an efficiency comparable to previous discriminative approaches. Furthermore, after being trained, our model can be easily transferred to new likelihood terms to solve untrained tasks, or be combined with existing priors to further improve image restoration quality.