Abstract

Establishing dense correspondences reliably between a pair of images is an important vision task with many applications. Though signifificant advance has been made towards estimating dense stereo and optical flflow fifields for two images adjacent in viewpoint or in time, building reliable dense correspondence fifields for two general images still remains largely unsolved. For instance, two given images sharing some content exhibit dramatic photometric and geometric variations, or they depict different 3D scenes of similar scene characteristics. Fundamental challenges to such an image or scene alignment task are often multifold, which render many existing techniques fall short of producing dense correspondences robustly and effificiently. This paper presents a novel approach called DAISY fifilter flflow (DFF) to address this challenging task. Inspired by the recent PatchMatch Filter technique, we leverage and extend a few established methods: 1) DAISY descriptors, 2) fifilter-based effificient flflow inference, and 3) the PatchMatch fast search. Coupling and optimizing these modules seamlessly with image segments as the bridge, the proposed DFF approach enables effificiently performing dense descriptor-based correspondence fifield estimation in a generalized high-dimensional label space, which is augmented by scales and rotations. Experiments on a variety of challenging scenes show that our DFF approach estimates spatially coherent yet discontinuity-preserving image alignment results both robustly and effificiently.