PixRadio: a new anaglyphic reversion technique based on radiometric differences reduction

Abstract

Anaglyph Stereo Matching is a particular, harder, case of the widely studied Stereo Matching algorithms. When applied to Anaglyph Reversion problem helps to improve stereo content storage and transmission, stereoscopic visualization independence and access to legacy anaglyph content available on the Web. However, the reversion process is not trivial since anaglyphs have high radiometric differences between the two views of a stereo pair of images, preventing standard stereo matching algorithms to be directly used. Different from related work, this paper presents a new pixel descriptor specially designed to deal with radiometric differences, allowing for the improvement of the final reconstructed stereo pair image quality. Experimental results show the proposed method presents, in average, better image quality when compared with related techniques.