Congote, JohnBarandiaran, JavierBarandiaran, IñigoRuiz, OscarCarlos Andujar and Javier Lluch2014-01-272014-01-272009978-3-905673-72-2https://doi.org/10.2312/LocalChapterEvents/CEIG/CEIG09/231-234Real-time depth extraction from stereo images is an important process in computer vision. This paper proposes a new implementation of the dynamic programming algorithm to calculate dense depth maps using the CUDA architecture achieving real-time performance with consumer graphics cards. We compare the running time of the algorithm against CPU implementation and demonstrate the scalability property of the algorithm by testing it on different graphics cards.Categories and Subject Descriptors (according to ACM CCS): ARTIFICIAL INTELLIGENCE [Computing Methodologies]: I.2.10 Vision and Scene Understanding3D/stereo scene analysis