Accurate Correspondences From Epipolar Plane Images

We present an algorithm for finding correspondences in epipolar plane images (EPIs). An EPI is a 2-dimensional spatio-temporal image obtained from a dense image sequence that is rectified so that each scene point is projected to the same row in all frames. Scenes with opaque Lambertian surfaces without occlusions are assumed. The approach is based on finding lines with similar intensities in an EPI for each image row separately, by dynamic programming. We focus on the correspondence accuracy. The high accuracy is enabled by a wide base line as in a stereo and by more data available. However, the matching is easier than in stereo as the displacement between neighboring frames is very small. No feature extraction is used, the algorithm is purely signal-based. We show the feasibility of the approach on synthetic data. A very good sub-pixel accuracy is demonstrated. The work in progress is reported aiming at using real data and sequences with occlusions.