Modulating Image Restoration with Continual Levels via Adaptive Feature Modification Layers

CVPR 2019  ·  Jingwen He, Chao Dong, Yu Qiao ·

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.

PDF Abstract CVPR 2019 PDF CVPR 2019 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Color Image Denoising CBSD68 sigma15 AdaFM-Net PSNR 34.1 # 2
Color Image Denoising CBSD68 sigma75 AdaFM-Net PSNR 26.35 # 1
Image Super-Resolution Set5 - 3x upscaling AdaFM-Net PSNR 34.34 # 11
Image Super-Resolution Set5 - 4x upscaling AdaFM-Net PSNR 32.13 # 26

Methods


No methods listed for this paper. Add relevant methods here