Stereo matching on low intensity quantization images

This paper addresses the problem of how the image intensity quantization affects the stereo matching algorithms. We compute the disparity using the stereo images represented by various intensity quantization levels. It is shown that, depending on the stereo matching algorithms, even the image pairs with low intensity quantization are able to produce fairly good disparity results. Experiments on Middlebury datasets demonstrate that the global algorithms such as GC and BP are suitable for stereo matching using low intensity quantization images.