Robust computation of optical flow in a multi-scale differential framework

By Joseph Weber, Jitendra Malik. 1993

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

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

In Computer Vision and Pattern Recognition

Citations in the corpus

Hypercolumns for object segmentation and fine-grained localization (2014, neutral): “This representation also proved useful for optical flow [39] and stereo [26].”
Cross Modal Distillation for Supervision Transfer (2015, positive): “Detection model For JHMDB we use the experimental setup from Gkioxari and Malik [13] and study the 21 class task.”
Optical flow modeling and computation: A survey (2015, methodology): “It has been achieved in [259] by considering K different linear filters fk providing a system of constancy equations to be solved at each pixel.”
Beyond Bounding Boxes: Precise Localization of Objects in Images (2015, unknown): “This representation also proved useful for optical flow [58] and stereo [37].”
PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume (2017, background): “First, traditional optical flow methods often pre-process the raw images to extract features that are invariant to shadows or lighting changes [4, 48].”
Noise characteristics and prior expectations in human visual speed perception (2006, background): “For speed perception, this relationship can be derived by assuming that image brightness is conserved [11, 12], and that measurements are corrupted by additive noise [13, 3, 14, 15].”
Ieee Transactions on Pattern Analysis and Machine Intelligence 1 Large Displacement Optical Flow: Descriptor Matching in Variational Motion Estimation (2011, unknown): “The use of richer descriptors in optical flow estimation goes back to Weber and Malik, who employed a multi-scale set of filter responses, so-called jets, in a Lucas-Kanade like setting [33].”
A Theoretical Framework for Convex Regularizers in PDE-Based Computation of Image Motion (2001, background): “Numerous generalizations to multiple constraint equations and/or different “conserved quantities” (replacing intensity) exist; see e.g. Fleet and Jepson (1990) and Weber and Malik (1995).”
Estimating Optical Flow in Segmented Images Using Variable-Order Parametric Models With Local Deformations (1996, unknown): “[45] 10:44 15:00 100% Fleet and Jepson [17] 4:29 11:24 34:1% Lucas and Kanade [31] 4:10 9:58 35:1% Weber and Malik [50] 3:42 5:35 45:2% Black and Anandan [11] 4:47 3:90 100% Black [10] 3:52 3:25 100% Parametric+Deformation 2:29 2:25 100% Table 1: Comparison of various optical flow algorithms.”