End-to-end Alternating Optimization for Blind Super Resolution

Previous methods decompose the blind super-resolution (SR) problem into two sequential steps: textiti) estimating the blur kernel from given low-resolution (LR) image and textitii) restoring the SR image based on the estimated kernel. This two-step solution involves two independently trained models, which may not be well compatible with each other. A small estimation error of the first step could cause a severe performance drop of the second one. While on the other hand, the first step can only utilize limited information from the LR image, which makes it difficult to predict a highly accurate blur kernel. Towards these issues, instead of considering these two steps separately, we adopt an alternating optimization algorithm, which can estimate the blur kernel and restore the SR image in a single model. Specifically, we design two convolutional neural modules, namely textitRestorer and textitEstimator. textitRestorer restores the SR image based on the predicted kernel, and textitEstimator estimates the blur kernel with the help of the restored SR image. We alternate these two modules repeatedly and unfold this process to form an end-to-end trainable network. In this way, textitEstimator utilizes information from both LR and SR images, which makes the estimation of the blur kernel easier. More importantly, textitRestorer is trained with the kernel estimated by textitEstimator, instead of the ground-truth kernel, thus textitRestorer could be more tolerant to the estimation error of textitEstimator. Extensive experiments on synthetic datasets and real-world images show that our model can largely outperform state-of-the-art methods and produce more visually favorable results at a much higher speed. The source code is available at urlhttps://github.com/greatlog/DAN.git.