Perceiving Systems, Computer Vision

Middlebury Optical Flow Dataset and Benchmark

2011-03-13


The Middlebury flow dataset has been a de-facto standard in the field since 2007. The dataset introduced several innovations. It is the first dataset to contain real image sequences with independent motions, and ground truth optical flow. Second, it provides realistically rendered synthetic scenes with ground truth flow. It also includes a frame interpolation task using real video sequences. While, by today's standards, the dataset is small and the sequences somewhat simple, it remains a useful tool for evaluating the generality of optical flow methods.

Author(s): Simon Baker and Daniel Scharstein and J.P. Lewis and Stefan Roth and Michael J. Black and Richard Szeliski
Department(s): Perceiving Systems
Publication(s): A Database and Evaluation Methodology for Optical Flow
A Database and Evaluation Methodology for Optical Flow
Authors: Simon Baker and Daniel Scharstein and J.P. Lewis and Stefan Roth and Michael J. Black and Richard Szeliski
Release Date: 2011-03-13
External Link: http://vision.middlebury.edu/flow/