Abstract
In image restoration tasks, learning from discrete and fixed restoration levels, deep models cannot be easily generalized to data of continuous and unseen levels. 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.
Abstract (translated)
在图像恢复任务中，从离散和固定的恢复层次学习，深度模型不能很容易地推广到连续和不可见层次的数据。我们提出了一个统一的CNN框架，该框架包含的附加参数比一个单一的级别模型少，但可以处理开始和结束级别之间的任意恢复级别。附加模块，即ADAFM层，对信道进行特征修正，可以使模型适应另一个高精度的恢复级别。
URL
https://arxiv.org/abs/1904.08118
