arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1604.05933cs.CV
收藏

模糊中的参数化对象运动

Parametric Object Motion from Blur

Department of Computer Science, TU Darmstadt(达姆施塔特工业大学计算机科学系)

Jochen Gast, Anita Sellent, Stefan Roth

摘要:

运动模糊会对许多视觉任务产生不利影响,因此通常被认为是一种滋扰。相反,我们将运动模糊视为一个有用的信号,可以从单个图像中计算对象的运动。借鉴成功的联合分割和参数运动模型的背景下,光流估计,我们提出了一个参数化的对象运动模型相结合的分割掩模,利用本地化,非均匀运动模糊。我们的参数图像形成模型是可微的w.r.t.的运动参数,这使我们能够概括的边缘似然技术,从均匀盲去模糊本地化,非均匀模糊。一个两阶段的管道,首先在导数空间,然后在图像空间,允许估计参数对象运动以及运动分割从一个单一的图像。我们的实验表明,它的能力,以应付非常具有挑战性的情况下,对象运动模糊。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑