Analyzing Spatially-varying Blur


Ayan Chakrabarti; Todd Zickler; William T. Freeman


Blur is caused by a pixel receiving light from multiple scene points, and in many cases, such as object motion, the induced blur varies spatially across the image plane. However, the seemingly straight-forward task of estimating spatially-varying blur from a single image has proved hard to accomplish reliably. This work considers such blur and makes two contributions: a local blur cue that measures the likelihood of a small neighborhood being blurred by a candidate blur kernel; and an algorithm that, given an image, simultaneously selects a motion blur kernel and segments the region that it affects. The methods are shown to perform well on a diversity of images.

Project Page:



BibTex entry

@proceedings { 254, title = {Analyzing Spatially-varying Blur}, year = {2010}, month = {13/06/2010}, address = {San Francisco, CA, USA}, author = {Ayan Chakrabarti and Todd Zickler and William T. Freeman} }