Efficient Multi-scale Network with Learnable Discrete Wavelet Transform for Blind Motion Deblurring

arXiv:2401.00027v2 Announce Type: replace
Abstract: Coarse-to-fine schemes are widely used in traditional single-image motion deblur; however, in the context of deep learning, existing multi-scale algorithms not only require the use of complex modules for feature fusion of low-scale RGB images and deep semantics, but also manually generate low-resolution pairs of images that do not have sufficient confidence. In this work, we propose a multi-scale network based on single-input and multiple-outputs(SIMO) for motion deblurring. This simplifies the complexity of algorithms based …

abstract algorithms arxiv blind context cs.cv deep learning feature fusion generate however image images low modules network scale semantics type wavelet