Performance Evaluation of 3D Correspondence Grouping Algorithms
This work provides a comparative analysis for researchers and practitioners in computer vision to select appropriate algorithms for tasks relying on feature correspondences, but it is incremental as it focuses on evaluation rather than introducing new methods.
This paper conducted a comprehensive evaluation of several 3D correspondence grouping algorithms across three benchmarks for shape retrieval, 3D object recognition, and point cloud registration, analyzing their performance and efficiency under various nuisances like noise and occlusion.
This paper presents a thorough evaluation of several widely-used 3D correspondence grouping algorithms, motived by their significance in vision tasks relying on correct feature correspondences. A good correspondence grouping algorithm is desired to retrieve as many as inliers from initial feature matches, giving a rise in both precision and recall. Towards this rule, we deploy the experiments on three benchmarks respectively addressing shape retrieval, 3D object recognition and point cloud registration scenarios. The variety in application context brings a rich category of nuisances including noise, varying point densities, clutter, occlusion and partial overlaps. It also results to different ratios of inliers and correspondence distributions for comprehensive evaluation. Based on the quantitative outcomes, we give a summarization of the merits/demerits of the evaluated algorithms from both performance and efficiency perspectives.