Parametric Object Motion from Blur
This addresses the problem of motion estimation for computer vision applications, offering a novel approach to leverage blur, but it is incremental as it builds on existing segmentation and parametric motion models.
The paper tackled the problem of estimating object motion from a single motion-blurred image by treating blur as a useful signal, and it achieved the ability to handle very challenging cases of object motion blur through a two-stage pipeline.
Motion blur can adversely affect a number of vision tasks, hence it is generally considered a nuisance. We instead treat motion blur as a useful signal that allows to compute the motion of objects from a single image. Drawing on the success of joint segmentation and parametric motion 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 us to 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.