Non-Local Auto-Encoder With Collaborative Stabilization for Image Restoration

Deep neural networks have been applied to image restoration to achieve the top-level performance. From a neuroscience perspective, the layerwise abstraction of knowledge in a deep neural network can, to some extent, reveal the mechanisms of how visual cues are processed in human brain. A pivotal property of human brain is that similar visual cues can stimulate the same neuron to induce similar neurological signals. However, conventional neural networks do not consider this property, and the resulting models are, as a result, unstable regarding their internal propagation. In this paper, we develop the (stacked) non-local auto-encoder, which exploits self-similar information in natural images for stability. We propose that similar inputs should induce similar network propagation. This is achieved by constraining the difference between the hidden representations of non-local similar image blocks during training. By applying the proposed model to image restoration, we then develop a collaborative stabilization step to further rectify forward propagation. To obtain a reliable deep model, we employ several strategies to simplify training and improve testing. Extensive image restoration experiments, including image denoising and super-resolution, demonstrate the effectiveness of the proposed method.