What is "Ground Truth"? The term originates in remote sensing: for example, elevation maps generated from aerial photographs must be related to the true elevation and location of features as measured on the ground. In computer vision, we need to know the true depth or true object motion if we want to evaluate the performance of stereo vision or optical flow algorithms.
In this talk I will show different techniques for creating image datasets with ground-truth geometry, including structured lighting, laser and CT scanners, and hidden fluorescent texture. I will demonstrate the Middlebury stereo and optical flow benchmarks, created in collaboration with undergraduates, which are used by researchers around the world. I will also discuss how data with ground truth can aid in developing new algorithms.