Recovering Stereo Pairs from Anaglyphs

Armand Joulin, Sing Bing Kang
2013 2013 IEEE Conference on Computer Vision and Pattern Recognition  
An anaglyph is a single image created by selecting complementary colors from a stereo color pair; the user can perceive depth by viewing it through color-filtered glasses. We propose a technique to reconstruct the original color stereo pair given such an anaglyph. We modified SIFT-Flow and use it to initially match the different color channels across the two views. Our technique then iteratively refines the matches, selects the good matches (which defines the "anchor" colors), and propagates
more » ... anchor colors. We use a diffusion-based technique for the color propagation, and added a step to suppress unwanted colors. Results on a variety of inputs demonstrate the robustness of our technique. We also extended our method to anaglyph videos by using optic flow between time frames.
doi:10.1109/cvpr.2013.44 dblp:conf/cvpr/JoulinK13 fatcat:ltfv2t7n4nh3pomusoewv5iq7y