# Blur More To Deblur Better: Multi-Blur2Deblur For Efficient Video Deblurring

arXiv: https://arxiv.org/abs/2012.12507 · HTML: https://mlsanity.com/paper/2012.12507/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Dec 2020.

## Built on by (most cited first, 3 of 3)

- [Meta Transferring for Deblurring](https://mlsanity.com/paper/2210.08036/) (2022)
- [Deformable Convolutions and LSTM-based Flexible Event Frame Fusion Network for Motion Deblurring](https://mlsanity.com/paper/2306.00834/) (2023)
- [Pay Attention to Hidden States for Video Deblurring: Ping-Pong Recurrent Neural Networks and Selective Non-Local Attention](https://mlsanity.com/paper/2203.16063/) (2022)

## Abstract (arXiv)

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.