Blur More To Deblur Better: Multi-Blur2Deblur For Efficient Video Deblurring
This work offers an incremental improvement in video deblurring performance for computer vision researchers and applications requiring clearer video footage.
This paper introduces Multi-Blur2Deblur (MB2D), a new approach for video deblurring that leverages more blurred images as additional inputs. It proposes a Multi-Blurring Recurrent Neural Network (MBRNN) to synthesize these blurred images, which significantly enhances existing deblurring methods and achieves state-of-the-art performance on GoPro and Su datasets.
One of the key components for video deblurring is how to exploit neighboring frames. Recent state-of-the-art methods either used aligned adjacent frames to the center frame or propagated the information on past frames to the current frame recurrently. Here we propose multi-blur-to-deblur (MB2D), a novel concept to exploit neighboring frames for efficient video deblurring. Firstly, inspired by unsharp masking, we argue that using more blurred images with long exposures as additional inputs significantly improves performance. Secondly, we propose multi-blurring recurrent neural network (MBRNN) that can synthesize more blurred images from neighboring frames, yielding substantially improved performance with existing video deblurring methods. Lastly, we propose multi-scale deblurring with connecting recurrent feature map from MBRNN (MSDR) to achieve state-of-the-art performance on the popular GoPro and Su datasets in fast and memory efficient ways.