Skip to main content

Burst deblurring: Removing camera shake through fourier burst accumulation

Publication ,  Conference
Delbracio, M; Sapiro, G
Published in: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
October 14, 2015

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.

Duke Scholars

Published In

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

DOI

ISSN

1063-6919

Publication Date

October 14, 2015

Volume

07-12-June-2015

Start / End Page

2385 / 2393
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Delbracio, M., & Sapiro, G. (2015). Burst deblurring: Removing camera shake through fourier burst accumulation. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Vol. 07-12-June-2015, pp. 2385–2393). https://doi.org/10.1109/CVPR.2015.7298852
Delbracio, M., and G. Sapiro. “Burst deblurring: Removing camera shake through fourier burst accumulation.” In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 07-12-June-2015:2385–93, 2015. https://doi.org/10.1109/CVPR.2015.7298852.
Delbracio M, Sapiro G. Burst deblurring: Removing camera shake through fourier burst accumulation. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2015. p. 2385–93.
Delbracio, M., and G. Sapiro. “Burst deblurring: Removing camera shake through fourier burst accumulation.” Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 07-12-June-2015, 2015, pp. 2385–93. Scopus, doi:10.1109/CVPR.2015.7298852.
Delbracio M, Sapiro G. Burst deblurring: Removing camera shake through fourier burst accumulation. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2015. p. 2385–2393.

Published In

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

DOI

ISSN

1063-6919

Publication Date

October 14, 2015

Volume

07-12-June-2015

Start / End Page

2385 / 2393