Shape matching: similarity measures and algorithms

526 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

CrossTransformers: spatially-aware few-shot transfer (2020, background): “The classical example of this is the centaur that appeared in several early papers on visual representation [12, 40, 87], where the parts from the human and horse composed the centaur.”
Supervised Evaluation of Image Segmentation and Object Proposal Techniques (2016, background): “ures that specifically evaluate, for instance, how similar the represented shapes are [40], [41], perception-inspired losses [33], [42], etc.”
Sketch-based modeling: A survey (2009, unknown): “This problem—matching 2D shapes—has been studied in computer vision, mostly comparing silhouettes and contours via image-based methods (see Veltkamp [79] for a good introduction).”
Partial Similarity of Objects, or How to Compare a Centaur to a Horse (2009, background): “Figure 1 (inspired by Jacobs et al. 2000; see also Veltkamp 2001; Latecki et al. 2005) shows a centaur—a half-equine half-human mythological creature.”
The Princeton Shape Benchmark (2004, result): “Despite decades of research on 3D shape representations and matching algorithms [20, 33], there still are no standard ways of comparing the results achieved with different methods.”