School of Computing, National University of Singapore, Singapore.
IEEE Trans Pattern Anal Mach Intell. 2011 Nov;33(11):2329-36. doi: 10.1109/TPAMI.2011.93.
This paper addresses the problem of matting motion blurred objects from a single image. Existing single image matting methods are designed to extract static objects that have fractional pixel occupancy. This arises because the physical scene object has a finer resolution than the discrete image pixel and therefore only occupies a fraction of the pixel. For a motion blurred object, however, fractional pixel occupancy is attributed to the object’s motion over the exposure period. While conventional matting techniques can be used to matte motion blurred objects, they are not formulated in a manner that considers the object’s motion and tend to work only when the object is on a homogeneous background. We show how to obtain better alpha mattes by introducing a regularization term in the matting formulation to account for the object’s motion. In addition, we outline a method for estimating local object motion based on local gradient statistics from the original image. For the sake of completeness, we also discuss how user markup can be used to denote the local direction in lieu of motion estimation. Improvements to alpha mattes computed with our regularization are demonstrated on a variety of examples.
本文解决了从单张图像中提取运动模糊物体的问题。现有的单图像抠图方法旨在提取具有分数像素占用的静态物体。这是因为物理场景物体的分辨率比离散图像像素更精细，因此只占用像素的一部分。然而，对于运动模糊的物体，分数像素占用是由于物体在曝光期间的运动造成的。虽然传统的抠图技术可以用于抠图运动模糊的物体，但它们的公式化方式并没有考虑到物体的运动，并且往往只在物体处于均匀背景时才有效。我们通过在抠图公式中引入正则化项来考虑物体的运动，展示了如何获得更好的 alpha 遮罩。此外，我们概述了一种基于原始图像中局部梯度统计信息来估计局部物体运动的方法。为了完整性，我们还讨论了如何使用用户标记来表示局部方向，而不是运动估计。我们的正则化方法计算的 alpha 遮罩在各种示例中得到了改进。
