Scale-recurrent Network for Deep Image Deblurring
It addresses image deblurring for applications like photography and computer vision, but is incremental as it builds on existing coarse-to-fine schemes.
The paper tackles single image deblurring by proposing a Scale-recurrent Network (SRN-DeblurNet) that uses a coarse-to-fine pyramid strategy, resulting in better quality outputs than state-of-the-art methods on large-scale datasets with complex motion.
In single image deblurring, the "coarse-to-fine" scheme, i.e. gradually restoring the sharp image on different resolutions in a pyramid, is very successful in both traditional optimization-based methods and recent neural-network-based approaches. In this paper, we investigate this strategy and propose a Scale-recurrent Network (SRN-DeblurNet) for this deblurring task. Compared with the many recent learning-based approaches in [25], it has a simpler network structure, a smaller number of parameters and is easier to train. We evaluate our method on large-scale deblurring datasets with complex motion. Results show that our method can produce better quality results than state-of-the-arts, both quantitatively and qualitatively.