Self-Tuned Deep Super Resolution
This work addresses image super-resolution for computer vision applications, representing an incremental advancement by combining existing techniques with reliability considerations.
The paper tackles image super-resolution by proposing a deep joint model that leverages both external and self-similarities, resulting in noticeable performance improvements quantitatively and perceptually across a wide range of images.
Deep learning has been successfully applied to image super resolution (SR). In this paper, we propose a deep joint super resolution (DJSR) model to exploit both external and self similarities for SR. A Stacked Denoising Convolutional Auto Encoder (SDCAE) is first pre-trained on external examples with proper data augmentations. It is then fine-tuned with multi-scale self examples from each input, where the reliability of self examples is explicitly taken into account. We also enhance the model performance by sub-model training and selection. The DJSR model is extensively evaluated and compared with state-of-the-arts, and show noticeable performance improvements both quantitatively and perceptually on a wide range of images.