Learning to Extract a Video Sequence from a Single Motion-Blurred Image

摘要: We present a method to extract video sequence from single motion-blurred image. Motion-blurred images are the result of an averaging process, where instant frames accumulated over time during exposure sensor. Unfortunately, reversing this process is nontrivial. Firstly, destroys temporal ordering frames. Secondly, recovery frame blind deconvolution task, which highly ill-posed. deep learning scheme that gradually reconstructs by sequentially extracting pairs Our main contribution introduce loss functions invariant order. This lets neural network choose training what output among possible combinations. also address ill-posedness deblurring designing with large receptive field and implemented via resampling achieve higher computational efficiency. proposed can successfully retrieve sharp image sequences motion blurred generalize well on synthetic real datasets captured different cameras.