Real-Time Subpixel Fast Bilateral Stereo
This work addresses the speed issue for real-time robotic systems, but it is incremental as it applies an existing method to new hardware.
The paper tackled the computational bottleneck of bilateral filtering in stereo vision by implementing fast bilateral stereo on a GPU, achieving real-time performance on the Middlebury datasets.
Stereo vision technique has been widely used in robotic systems to acquire 3-D information. In recent years, many researchers have applied bilateral filtering in stereo vision to adaptively aggregate the matching costs. This has greatly improved the accuracy of the estimated disparity maps. However, the process of filtering the whole cost volume is very time consuming and therefore the researchers have to resort to some powerful hardware for the real-time purpose. This paper presents the implementation of fast bilateral stereo on a state-of-the-art GPU. By highly exploiting the parallel computing architecture of the GPU, the fast bilateral stereo performs in real time when processing the Middlebury stereo datasets.