Spatial Clustering Guided Two-View Multi-Structural Deterministic Geometric Model Fitting

Abstract

This paper addresses the two-view geometric model fitting problem on the multi-structural data with severe outliers for providing reliable and consistent fitting results. The key idea is to adopt spatial clustering to guide deterministically sample minimum subsets. Specifically, we firstly improve the effectiveness of spatial clustering with good neighbors that preserve the consensus of neighborhood elements and neighborhood topology, for enhancing the quality of sampled minimum subsets. Then we further design a multi-scale fusion strategy, which not only boosts more high-quality minimum subsets, but also enables our method to cover all model instances in data. Moreover, we propose a simple and effective model selection algorithm to estimate the parameters of model instances in data. The final proposed method is able to guarantee fast, accurate and stable model fitting results for the multi-structural data. In addition, we construct two large labeled datasets, for homography and fundamental matrix estimation, respectively. Experimental results on real images from six datasets show the significant superiority of the proposed method on both accuracy and speed over several state-of-the-art alternatives. Especially for the MS-COCO-F and YFCC100M-F datasets, the proposed method yields a performance boost of over three times on segmentation error, parameter error and the CPU time.