Burst Deblurring: Removing Camera Shake Through Fourier Burst Accumulation

Mauricio Delbracio, Guillermo Sapiro; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 2385-2393

Abstract


Numerous recent approaches attempt to remove image blur due to camera shake, either with one or multiple input images, by explicitly solving an inverse and inherently ill-posed deconvolution problem. If the photographer takes a burst of images, a modality available in virtually all modern digital cameras, we show that it is possible to combine them to get a clean sharp version. This is done without explicitly solving any blur estimation and subsequent inverse problem. The proposed algorithm is strikingly simple: it performs a weighted average in the Fourier domain, with weights depending on the Fourier spectrum magnitude. The method's rationale is that camera shake has a random nature and therefore each image in the burst is generally blurred differently. Experiments with real camera data show that the proposed Fourier Burst Accumulation algorithm achieves state-of-the-art results an order of magnitude faster, with simplicity for on-board implementation on camera phones.

Related Material


[pdf]
[bibtex]
@InProceedings{Delbracio_2015_CVPR,
author = {Delbracio, Mauricio and Sapiro, Guillermo},
title = {Burst Deblurring: Removing Camera Shake Through Fourier Burst Accumulation},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2015}
}