Sparse Stereo by Edge-Based Search Using Dynamic Programming
Jonas Witt, Uwe Weltin · 2016
In this paper, a novel edge-based stereo matching technique is presented. Depth discontinuities are specif-ically accounted for in the choice of support regions. We employ dynamic programming along edge-segments to efficiently enforce inter-scanline consistency. Although not performing a global optimization over the whole image we show that our approach performs success-fully on the Middlebury benchmark datasets1 while be-ing computationally feasible in real-time. 1.