Joint Depth Estimation and Camera Shake Removal from Single Blurry Image


Zhe Hu§      Li Xu      Ming-Hsuan Yang§

§UC Merced       Lenovo R & T

IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2014)

Abstract

Camera shake during exposure time often results in spatially variant blur effect of the image. The non-uniform blur effect is not only caused by the camera motion, but also the depth variation of the scene. The objects close to the camera sensors are likely to appear more blurry than those at a distance in such cases. However, recent non-uniform deblurring methods do not explicitly consider the depth factor or assume fronto-parallel scenes with constant depth for simplicity. While single image non-uniform deblurring is a challenging problem, the blurry results in fact contain depth information which can be exploited. We propose to jointly estimate scene depth and remove non-uniform blur caused by camera motion via exploiting their underlying geometric relationships, with only single blurry image as input. To this end, we present a unified layer-based model for depth-involved deblurring. We provide a novel layerbased solution using matting to partition the layers and an expectation-maximization scheme to solve this problem. This approach largely reduces the number of unknowns and makes the problem tractable. Experiments on challenging examples demonstrate that both depth and camera shake removal can be well addressed within the unified framework.

Paper and MATLAB code

The paper and MATLAB code can be found here. [PDF] [Poster] MATLAB code coming soon

BibTex

@inproceedings{hu_cvpr2014_depthdeblur,
title = {Joint Depth Estimation and Camera Shake Removal from Single Blurry Image},
author = {Zhe Hu, Li Xu and Ming-Hsuan Yang},
journal = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2014)},
year = {2014}
}