Learning to Deblur
This work addresses image deblurring for computer vision applications, but it is incremental as it builds on existing neural network methods.
The paper tackles blind image deconvolution by proposing a learning-based approach using a deep layered architecture, achieving competitive performance in both quality and runtime on artificially generated training examples.
We describe a learning-based approach to blind image deconvolution. It uses a deep layered architecture, parts of which are borrowed from recent work on neural network learning, and parts of which incorporate computations that are specific to image deconvolution. The system is trained end-to-end on a set of artificially generated training examples, enabling competitive performance in blind deconvolution, both with respect to quality and runtime.