Extreme Channel Prior Embedded Network for Dynamic Scene Deblurring
This work addresses image deblurring for computer vision applications, presenting an incremental improvement by incorporating known priors into a neural network framework.
The authors tackled dynamic scene deblurring by proposing an Extreme Channel Prior embedded Network (ECPeNet) that integrates extreme channel priors and sparse regularization into a multi-scale architecture, achieving favorable performance against state-of-the-art methods on GoPro and Kohler datasets.
Recent years have witnessed the significant progress on convolutional neural networks (CNNs) in dynamic scene deblurring. While CNN models are generally learned by the reconstruction loss defined on training data, incorporating suitable image priors as well as regularization terms into the network architecture could boost the deblurring performance. In this work, we propose an Extreme Channel Prior embedded Network (ECPeNet) to plug the extreme channel priors (i.e., priors on dark and bright channels) into a network architecture for effective dynamic scene deblurring. A novel trainable extreme channel prior embedded layer (ECPeL) is developed to aggregate both extreme channel and blurry image representations, and sparse regularization is introduced to regularize the ECPeNet model learning. Furthermore, we present an effective multi-scale network architecture that works in both coarse-to-fine and fine-to-coarse manners for better exploiting information flow across scales. Experimental results on GoPro and Kohler datasets show that our proposed ECPeNet performs favorably against state-of-the-art deep image deblurring methods in terms of both quantitative metrics and visual quality.