Joint motion estimation and segmentation of complex scenes with label costs and occlusion modeling

67 citations recorded by the source corpus.

How researchers see this paper

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

Video Segmentation by Tracking Many Figure-Ground Segments (2013, unknown): “[9] [32] uses variational approximations.”
Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation (2019, methodology): “Other methods [2, 7, 25, 28, 50, 57, 60] model occlusions in a joint energy and utilize them as additional evi-”
Occlusion Aware Unsupervised Learning of Optical Flow (2017, background): “The first group treats occlusion as outliers and predict target pixels in the occluded regions as a constant value or through interpolation [47, 3, 4, 52].”
A Fully-Connected Layered Model of Foreground and Background Flow (2013, background): “[29] can handle scenes with hundreds of labels and handle occlusions by an outlier process without geometric modeling.”
Optical flow modeling and computation: A survey (2015, methodology): “For example, the results reported in [233,244] are obtained with an initialization by the result of the methods of [231,271] respectively.”
3D Scene Flow Estimation with a Piecewise Rigid Scene Model (2015, methodology): “General 2D optical ﬂow is computed by Unger et al. (2012), who parameterize the motion of each segment with 2D afﬁne transformations, and also allow for occlusion handling.”
Piecewise Rigid Scene Flow (2013, methodology): “[17] compute optical flow by parameterizing the motion per segment with 2D affine transformations, and also perform occlusion handling.”