Abstract

Binary keypoint descriptors provide an effificient alternative to their flfloating-point competitors as they enable faster processing while requiring less memory. In this paper, we propose a novel framework to learn an extremely compact binary descriptor we call BinBoost that is very robust to illumination and viewpoint changes. Each bit of our descriptor is computed with a boosted binary hash function, and we show how to effificiently optimize the different hash functions so that they complement each other, which is key to compactness and robustness. The hash functions rely on weak learners that are applied directly to the image patches, which frees us from any intermediate representation and lets us automatically learn the image gradient pooling confifiguration of the fifinal descriptor. Our resulting descriptor signifificantly outperforms the state-of-the-art binary descriptors and performs similarly to the best flfloating-point descriptors at a fraction of the matching time and memory footprint.