Abstract

In this work we make use of recent advances in data driven classifification to improve standard approaches for binocular stereo matching and single view depth estimation. Surface normal direction estimation has become feasible and shown to work reliably on state of the art benchmark datasets. Information about the surface orientation contributes crucial information about the scene geometry in cases where standard approaches struggle. We describe, how the responses of such a classififier can be included in global stereo matching approaches. One of the strengths of our approach is, that we can use the classififier responses for a whole set of directions and let the fifinal optimization decide about the surface orientation. This is important in cases where based on the classififier, multiple different surface orientations seem likely. We evaluate our method on two challenging real-world datasets for the two proposed applications. For the binocular stereo matching we use road scene imagery taken from a car and for the single view depth estimation we use images taken in indoor environments.