Scaled-neighborhood Patches Fusion for Multi-view Stereopsis

In this paper, we present a multi-view stereo reconstruction approach which fuses scaled-neighborhood information. PMVS proposed by Furukawa is one of the most excellent algorithms, and it has a good performance on many datasets both the accuracy and the completeness. However, there are still further improvements on this algorithm. PMVS cannot perform well in the presence of slanted surfaces, which are usually imaged at oblique angles. According to these aspects, on the one hand we propose to estimate the initial normal of every seed patch via fitting quadrics with scaled-neighborhood patches, which greatly improves the accuracy of the normal. On the other hand, we present to compute scaled-window for the further optimization based on texture. And it has been tested that employing the scaled-window will dramatically smooth the surfaces and enhance the reconstruction precision.