3D Models Retrieval Using Earth Mover’s Distance

Zemzami, Omar Ait; Aksasse, H.; Ouanan, Mohammed; Aksasse, Brahim

doi:10.12816/0006188

Cited by 1 publication

(1 citation statement)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The basic similarity measures are the Manhattan/L1 and Euclidean/L2 distance [29], mostly due to their simplicity and computational efficiency. Other distance measures have also been widely applied in 3D object retrieval, such as the Hausdorff distance applied to [30], the earth mover's distance applied to [31], and bipartite graph matching applied to [9]. Investigations have also been made to measure the dissimilarity between non-rigid 3D models.…”

Section: B Similarity Measurementioning

confidence: 99%

3D Point Cloud Retrieval With Bidirectional Feature Match

2019

View full text Add to dashboard Cite

In the recent decade, the development of 3D scanners brings the expansion of 3D models, which yields in the increase of demand for developing effective 3D point cloud retrieval methods using only unorganized point clouds instead of mesh data. In this paper, we propose a meshing-free framework for point cloud retrieval by exploiting a bidirectional similarity measurement on local features. Specifically, we first introduce an effective pipeline for keypoint selection by applying principal component analysis to pose normalization and thresholding local similarity of normals. Then, a point cloud based feature descriptor is employed to compute local feature descriptors directly from point clouds. Finally, we propose a bidirectional feature match strategy to handle the similarity measure. Experimental evaluation on a publicly available benchmark demonstrates the effectiveness of our framework and shows it can outperform other alternatives involving state-of-the-art techniques. INDEX TERMS Point cloud retrieval, 3D shape retrieval, bidirectional feature match.

show abstract

Section: B Similarity Measurementioning

confidence: 99%