Abstract

Motion blur can adversely affect a number of visiontasks, hence it is generally considered a nuisance. We in-stead treat motion blur as a useful signal that allows to com-pute the motion of objects from a single image. Drawingon the success of joint segmentation and parametric mo-tion models in the context of optical flow estimation, we propose a parametric object motion model combined with a segmentation mask to exploit localized, non-uniform motion blur. Our parametric image formation model is differentiable w.r.t. the motion parameters, which enables usto generalize marginal-likelihood techniques from uniform blind deblurring to localized, non-uniform blur. A two-stage pipeline, first in derivative space and then in image space, allows to estimate both parametric object motion as well as a motion segmentation from a single image alone. Our experiments demonstrate its ability to cope with very challenging cases of object motion blur.