Defocus Magnification


Soonmin Bae   Frédo Durand

MIT CSAIL

Computer Graphics Forum, Volume 26, Issue 3 (Proc. of Eurographics 2007)



Abstract

A blurry background due to shallow depth of field is often desired for photographs such as portraits, but, unfortunately, small point-and-shoot cameras do not permit enough defocus because of the small diameter of their lenses. We present an image-processing technique that increases the defocus in an image to simulate the shallow depth of field of a lens with a larger aperture. Our technique estimates the spatially-varying amount of blur over the image, and then uses a simple image-based technique to increase defocus. We first estimate the size of the blur kernel at edges and then propagate this defocus measure over the image. Using our defocus map, we magnify the existing blurriness, which means that we blur blurry regions and keep sharp regions sharp. In contrast to more difficult problems such as depth from defocus, we do not require precise depth estimation and do not need to disambiguate textureless regions.





Acknowledgement

We thank the MIT Computer Graphics Group and the anonymous reviewers for their comments. This work was supported by a National Science Foundation CAREER award 0447561 "Transient Signal Processing for Realistic Imagery," an NSF Grant No. 0429739 "Parametric Analysis and Transfer of Pictorial Style," and a grant from Royal Dutch/Shell Group. Frédo Durand acknowledges a Microsoft Research New Faculty Fellowship, a Sloan Fellowship, and a Jamieson chair. Soonmin Bae is financially supported by the Samsung Scholarship.