High-quality motion deblurring from a single image

Abstract

Figure 1High quality single image motion-deblurring. The left sub-figure shows one captured image using a hand-held camera under dim light. It is severely blurred by an unknown kernel. The right sub-figure shows our deblurred image result computed by estimating both the blur kernel and the unblurred latent image. We show several close-ups of blurred/unblurred image regions for comparison. AbstractWe present a new algorithm for removing motion blur from a single image. Our method computes a deblurred image using a unified probabilistic model of both blur kernel estimation and unblurred image restoration. We present an analysis of the causes of common artifacts found in current deblurring methods, and then introduce several novel terms within this probabilistic model that are inspired by our analysis. These terms include a model of the spatial randomness of noise in the blurred image, as well a new local smoothness prior that reduces ringing artifacts by constraining contrast in the unblurred image wherever the blurred image exhibits low contrast. Finally, we describe an efficient optimization scheme that alternates between blur kernel estimation and unblurred image restoration until convergence. As a result of these steps, we are able to produce high quality deblurred results in low computation time. We are even able to produce results of comparable quality to techniques that require additional input images beyond a single blurry photograph, and to methods that require additional hardware.

Sparse Bayesian blind image deconvolution with parameter estimation

“…The most recent methods are based on a Bayesian framework, http://jivp.eurasipjournals.com/content/2012/1/20 and have addressed the removal of the camera motion from blurred photographs [12][13][14][15][16][17][18][19]. In [12] the unknown image and blur were estimated in a two step process.…”

“…Estimating camera motion has also been investigated in [13,14], where the unknown image and blur were estimated in a simultaneous fashion. Additionally, [14] concentrated on synthetic experiments where the performance of the algorithm was evaluated by the improvement in signal to noise ratio.…”

“…Additionally, [14] concentrated on synthetic experiments where the performance of the algorithm was evaluated by the improvement in signal to noise ratio. Also, in [13,14] the regularization parameters are not automatically estimated but rather heuristically chosen by the user at each iteration in order to yield an unknown image estimate with good visual quality. The major disadvantage of the methods proposed in [13,14] compared to the method proposed in [12] is the lack of parameter estimation.…”

“…Furthermore, we utilize the Bayesian framework to provide the estimates for all model parameters. Finally, we evaluate the performance of the proposed algorithm and provide comparisons with [12][13][14]16,19] by restoring blurred photographs taken by commercial cameras.…”

Implementation of Local Fourier Burst Accumulation for Video Deblurring

“…Existing single image deconvolution methods such as the one proposed by Shan et al [8] achieve excellent image quality by estimating both the blur kernel and the latent image. Although very attractive, these methods are not designed to process videos, mainly due to their high computational cost and to the requirement that the deblurring result must be coherent across frames to avoid jitter.…”