3D Correspondence Grouping with Compatibility Features
This addresses the challenge of accurate 3D correspondence grouping for computer vision applications, representing an incremental improvement with a novel feature representation.
The paper tackles the problem of 3D correspondence grouping by classifying initial correspondences into inliers and outliers, proposing a compatibility feature (CF) representation based on geometric constraints and using an MLP for classification, achieving the best overall performance compared to nine state-of-the-art methods on four benchmarks.
We present a simple yet effective method for 3D correspondence grouping. The objective is to accurately classify initial correspondences obtained by matching local geometric descriptors into inliers and outliers. Although the spatial distribution of correspondences is irregular, inliers are expected to be geometrically compatible with each other. Based on such observation, we propose a novel representation for 3D correspondences, dubbed compatibility feature (CF), to describe the consistencies within inliers and inconsistencies within outliers. CF consists of top-ranked compatibility scores of a candidate to other correspondences, which purely relies on robust and rotation-invariant geometric constraints. We then formulate the grouping problem as a classification problem for CF features, which is accomplished via a simple multilayer perceptron (MLP) network. Comparisons with nine state-of-the-art methods on four benchmarks demonstrate that: 1) CF is distinctive, robust, and rotation-invariant; 2) our CF-based method achieves the best overall performance and holds good generalization ability.