SIRA - An efficient method for retrieving stereo images from anaglyphs

Abstract

Anaglyph reversion aims to recover the best possible approximation of a stereo pair of images from an anaglyph. Possible applications include a range of practical situations like enabling visualization of legacy anaglyphs on the Web, saving storage/transmission bandwidth by encoding stereo pairs as anaglyphs before stereo visualization or enabling users to enjoy stereo visualization using any available device. The recovering process faces a challenging issue: the anaglyphic stereo matching. Different from regular stereo images, corresponding pixels in the left and right views of an anaglyph have dissimilar intensity values, lowering photometric consistency and thus turning the usual stereo matching algorithms not suitable. In this work we propose SIRA, an efficient method for anaglyph reversion, introducing a novel approach to find stereo correspondences based on a pixel descriptor developed to deal with anaglyphic photometric differences. The descriptor core idea is to model stereo pairs as time series, extracted from both views of an anaglyph. The series are then compared through a time series matching algorithm, providing a faster, yet accurate, pixels alignment. Occlusions are dealt with using a colorization strategy based on the nearest neighbor search. We evaluate SIRA’s computational efficiency and both objective and subjective image quality on the well-known Middlebury dataset. We also compared SIRA with state of the art related methods. The results show SIRA achieves equivalent image quality while consuming 26 times less computational resources, on average. Therefore, SIRA shows up as an effective and efficient method to convey anaglyph reversion, advantaging the aforementioned applications.