Binary Stereo Matching
This work addresses stereo matching for computer vision applications, offering an incremental efficiency improvement with binary computations.
The paper tackled stereo matching by introducing a binary-based cost computation and aggregation approach, achieving comparable performance to state-of-the-art local methods in quality and speed on the Middlebury benchmark and showing improved robustness under radiometric differences.
In this paper, we propose a novel binary-based cost computation and aggregation approach for stereo matching problem. The cost volume is constructed through bitwise operations on a series of binary strings. Then this approach is combined with traditional winner-take-all strategy, resulting in a new local stereo matching algorithm called binary stereo matching (BSM). Since core algorithm of BSM is based on binary and integer computations, it has a higher computational efficiency than previous methods. Experimental results on Middlebury benchmark show that BSM has comparable performance with state-of-the-art local stereo methods in terms of both quality and speed. Furthermore, experiments on images with radiometric differences demonstrate that BSM is more robust than previous methods under these changes, which is common under real illumination.