Li Xu, Jianing Chen, Jiaya Jia. A Segmentation Based Variational Model for Accurate Optical Flow Estimation. In David A. Forsyth, Philip H. S. Torr, Andrew Zisserman, editors, Computer Vision - ECCV 2008, 10th European Conference on Computer Vision, Marseille, France, October 12-18, 2008, Proceedings, Part I. Volume 5302 of Lecture Notes in Computer Science, pages 671-684, Springer, 2008. [doi]
Segmentation has gained in popularity in stereo matching. However, it is not trivial to incorporate it in optical flow estimation due to the possible non-rigid motion problem. In this paper, we describe a new optical flow scheme containing three phases. First, we partition the input images and integrate the segmentation information into a variational model where each of the segments is constrained by an affine motion. Then the errors brought in by segmentation are measured and stored in a confidence map. The final flow estimation is achieved through a global optimization phase that minimizes an energy function incorporating the confidence map. Extensive experiments show that the proposed method not only produces quantitatively accurate optical flow estimates but also preserves sharp motion boundaries, which makes the optical flow result usable in a number of computer vision applications, such as image/video segmentation and editing.