Self-Committee Approach for Image Restoration Problems using Convolutional Neural Network
This is an incremental improvement for image processing researchers, offering a simpler alternative to multi-network committee methods.
The paper tackles image restoration by proposing a self-committee method that uses a single CNN with transformed inputs to enhance results, achieving additional gains in denoising and super-resolution tasks.
There have been many discriminative learning methods using convolutional neural networks (CNN) for several image restoration problems, which learn the mapping function from a degraded input to the clean output. In this letter, we propose a self-committee method that can find enhanced restoration results from the multiple trial of a trained CNN with different but related inputs. Specifically, it is noted that the CNN sometimes finds different mapping functions when the input is transformed by a reversible transform and thus produces different but related outputs with the original. Hence averaging the outputs for several different transformed inputs can enhance the results as evidenced by the network committee methods. Unlike the conventional committee approaches that require several networks, the proposed method needs only a single network. Experimental results show that adding an additional transform as a committee always brings additional gain on image denoising and single image supre-resolution problems.