Motion Blur removal via Coupled Autoencoder
This addresses image deblurring for computer vision applications, but it appears incremental as it applies an existing transfer learning framework to a new problem.
The paper tackles motion blur removal by recasting deblurring as a transfer learning problem and solving it with a coupled autoencoder, resulting in better quality images and shorter operating times compared to state-of-the-art techniques.
In this paper a joint optimization technique has been proposed for coupled autoencoder which learns the autoencoder weights and coupling map (between source and target) simultaneously. The technique is applicable to any transfer learning problem. In this work, we propose a new formulation that recasts deblurring as a transfer learning problem, it is solved using the proposed coupled autoencoder. The proposed technique can operate on-the-fly, since it does not require solving any costly inverse problem. Experiments have been carried out on state-of-the-art techniques, our method yields better quality images in shorter operating times.