Partial matching of 3D shapes with priority-driven search

Priority-driven search is an algorithm for retrieving similar shapes from a large database of 3D objects. Given a query object and a database of target objects, all represented by sets of local 3D shape features, the algorithm produces a ranked list of the c best target objects sorted by how well any subset of k features on the query match features on the target object. To achieve this goal, the system maintains a priority queue of potential sets of feature correspondences (partial matches) sorted by a cost function accounting for both feature dissimilarity and the geometric deformation. Only partial matches that can possibly lead to the best full match are popped off the queue, and thus the system is able to find a provably optimal match while investigating only a small subset of potential matches. New methods based on feature distinction, feature correspondences at multiple scales, and feature difference ranking further improve search time and retrieval performance. In experiments with the Princeton Shape Benchmark, the algorithm provides significantly better classification rates than previously tested shape matching methods while returning the best matches in a few seconds per query.