Modulating Image Restoration with Continual Levels via Adaptive Feature Modification Layers
This addresses a practical limitation for real-world applications in image processing where flexible restoration levels are needed, representing a novel approach to a rarely explored problem.
The paper tackles the problem of enabling deep learning models for image restoration tasks, such as denoising and super-resolution, to handle continuous and unseen restoration levels, which existing methods fail to do. It proposes a unified CNN framework with AdaFM layers that achieves high accuracy in modulating restoration levels using few additional parameters, as demonstrated through extensive experiments on three tasks.
In image restoration tasks, like denoising and super resolution, continual modulation of restoration levels is of great importance for real-world applications, but has failed most of existing deep learning based image restoration methods. Learning from discrete and fixed restoration levels, deep models cannot be easily generalized to data of continuous and unseen levels. This topic is rarely touched in literature, due to the difficulty of modulating well-trained models with certain hyper-parameters. We make a step forward by proposing a unified CNN framework that consists of few additional parameters than a single-level model yet could handle arbitrary restoration levels between a start and an end level. The additional module, namely AdaFM layer, performs channel-wise feature modification, and can adapt a model to another restoration level with high accuracy. By simply tweaking an interpolation coefficient, the intermediate model - AdaFM-Net could generate smooth and continuous restoration effects without artifacts. Extensive experiments on three image restoration tasks demonstrate the effectiveness of both model training and modulation testing. Besides, we carefully investigate the properties of AdaFM layers, providing a detailed guidance on the usage of the proposed method.