Lin M H, Tomasi C
IEEE Trans Pattern Anal Mach Intell. 2004 Aug;26(8):1073-1078. doi: 10.1109/TPAMI.2004.54.
We propose a new binocular stereo algorithm that estimates scene structure as a collection of smooth surface patches. The disparities within each patch are modeled by a continuous-valued spline, while the extent of each patch is represented via a pixelwise partitioning of the images. Disparities and extents are alternately estimated in an iterative, energy minimization framework. Experimental results demonstrate that, for scenes consisting of smooth surfaces, the proposed algorithm significantly improves upon the state of the art.
我们提出了一种新的双目立体算法,该算法将场景结构估计为一组平滑表面补丁。每个补丁内的视差由连续值样条建模,而每个补丁的范围通过图像的逐像素划分来表示。视差和范围在一个迭代的能量最小化框架中交替估计。实验结果表明,对于由平滑表面组成的场景,该算法显著优于现有技术。