From Motion Blur to Motion Flow: a Deep Learning Solution for Removing Heterogeneous Motion Blur

被引:248
作者
Gong, Dong [1 ,2 ]
Yang, Jie [2 ]
Liu, Lingqiao [2 ,3 ]
Zhang, Yanning [1 ]
Reid, Ian [2 ,3 ]
Shen, Chunhua [2 ,3 ]
van den Hengel, Anton [2 ,3 ]
Shi, Qinfeng [2 ]
机构
[1] Northwestern Polytech Univ, Sch Comp Sci & Engn, Xian, Shaanxi, Peoples R China
[2] Univ Adelaide, Adelaide, SA, Australia
[3] Australian Ctr Robot Vis, Brisbane, Qld, Australia
来源
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) | 2017年
基金
澳大利亚研究理事会;
关键词
BLIND DECONVOLUTION;
D O I
10.1109/CVPR.2017.405
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Removing pixel-wise heterogeneous motion blur is challenging due to the ill-posed nature of the problem. The predominant solution is to estimate the blur kernel by adding a prior, but extensive literature on the subject indicates the difficulty in identifying a prior which is suitably informative, and general. Rather than imposing a prior based on theory, we propose instead to learn one from the data. Learning a prior over the latent image would require modeling all possible image content. The critical observation underpinning our approach, however, is that learning the motion flow instead allows the model to focus on the cause of the blur, irrespective of the image content. This is a much easier learning task, but it also avoids the iterative process through which latent image priors are typically applied. Our approach directly estimates the motion flow from the blurred image through a fully-convolutional deep neural network (FCN) and recovers the unblurred image from the estimated motion flow. Our FCN is the first universal end-to-end mapping from the blurred image to the dense motion flow. To train the FCN, we simulate motion flows to generate synthetic blurred-image-motion-flow pairs thus avoiding the need for human labeling. Extensive experiments on challenging realistic blurred images demonstrate that the proposed method outperforms the state-of-the-art.
引用
收藏
页码:3806 / 3815
页数:10
相关论文
共 47 条
  • [1] [Anonymous], CVPR
  • [2] [Anonymous], 2013, IEEE C COMP VIS PATT
  • [3] [Anonymous], IEEE C COMP VIS PATT
  • [4] [Anonymous], 2011, VISIGRAPP 2011. Communications in Computer and Information Science, DOI DOI 10.1007/978-3-642-32350-8_7
  • [5] [Anonymous], 2016, CVPR
  • [6] [Anonymous], 2015, PROC CVPR IEEE
  • [7] [Anonymous], 2009, ACM SIGGRAPH ASIA 20
  • [8] [Anonymous], IMAGE RESTORATION CO
  • [9] [Anonymous], 2006, P NEURAL INFORM PROC
  • [10] [Anonymous], ACM T GRAPHICS