On Benchmarking Optical Flow

By Brendan McCane, Kevin L. Novins, D. Crannitch, Ben Galvin. Computer Vision and Image Understanding, 2001

295 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.

When Can We Use KinectFusion for Ground Truth Acquisition (2012, methodology): “ing evaluation datasets for problems such as optical flow used short (< 14 frames) rendered sequences [4], [5], [6].”
Free Supervision from Video Games (2018, background): “[31] extend this to include the three dimensional scene and rendered objects.”
Playing for Data: Ground Truth from Computer Games (2016, background): “The use of synthetic data has been particularly significant in evaluating optical flow estimation due to the difficulty of obtaining accurate ground-truth flow measurements for real-world scenes [6, 7, 18, 32].”
Motion history image: its variants and applications (2012, methodology): “Optical flow methods [27,29,66,91,94,113,138,149,153] can be used for the generation of the MHI and motion segmentation for various purposes.”
A Database and Evaluation Methodology for Optical Flow (2007, background): “Most recently McCane et al. [12] provided more ground truth for real polyhedral scenes as well as graphics scenes of varying realism.”
A Naturalistic Open Source Movie for Optical Flow Evaluation (2012, background): “[10] introduced more realistic graphics sequences with independent motion.”