Abstract

We present an algorithm to reduce per-pixel search ranges for Markov Random Fields-based stereo algorithms. Our algorithm is based on the intuitions that reliably matched pixels need less regular- ization in the energy minimization and neighboring pixels should have similar disparity search ranges if their pixel values are similar. We pro- pose a novel bi-labeling process to classify reliable and unreliable pixels that incorporate left-right consistency checks. We then propagate the reliable disparities into unreliable regions to form a complete disparity map and construct per-pixel search ranges based on the difference be- tween the disparity map after propagation and the one computed from a winner-take-all method. Experimental results evaluated on the Middle- bury stereo benchmark show our proposed algorithm is able to achieve 77% average reduction rate while preserving satisfactory accuracy.