Estimating Optical Flow in Segmented Images Using Variable-Order Parametric Models With Local Deformations

By Michael J. Black, Allan D. Jepson. 1996

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Video Segmentation via Object Flow (2016, methodology): “To compute accurate optical flow fields, it is common to segment images or extract edges to preserve motion details around object boundaries [3, 43, 44, 47].”
Optical Flow with Semantic Segmentation and Localized Layers (2016, background): “Previous work [7, 59] segments the scene into patches according to color or other cues, and then fits parametric flow models within these.”
Optical flow modeling and computation: A survey (2015, methodology): “Generally, an independent coarse and cheap motion estimation is fused with the color image segmentation to overcome the lack of information [28,34,278].”
Layered image motion with explicit occlusions, temporal consistency, and depth ordering (2010, methodology): “Consequently, we f ormulate a hybrid model that combines a base affine motion with a robust Markov random field (MRF) mode l f deformationsfrom affine [6].”
A Database and Evaluation Methodology for Optical Flow (2007, methodology): “Several methods first segment the scene using non-motion cues and then estimate the flow in these regions [12,83].”
On 3D scene flow and structure estimation (2001, background): “However, the recovery of segmented or piecewise smooth flow field is notably difficult [ 5 ].”
A Quantitative Analysis of Current Practices in Optical Flow Estimation and the Principles Behind Them (2013, background): “…(Nagel and Enkelmann 1986; Sun et al. 2008; Wedel et al. 2009; Zimmer et al. 2011, 2009), rigidity constraints (Wedel et al. 2008a, 2009), an over-parameterized smoothness term (Nir et al. 2008), or image segmentation (Black and Jepson 1996; Lei and Yang 2009; Xu et al. 2008; Zitnick et al. 2005).”