3D Shape Matching with 3D Shape Contexts

By Marcel Körtgen, Gil-Joo Park, Marcin Novotni, Reinhard Klein. 2003

325 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/3379802b1e253726ab3979c4921cea1cff29a198

How researchers see this paper

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

Citations in the corpus

Interactive shape co-segmentation via label propagation (2014, background): “These widely recognized descriptors are the Shape Diameter Function (SDF) [31], the Conformal Factor (CF) [32], the Shape Contexts (SCs) [33,34], the Average Geodesic Distance (AGD) [35], and the geodesic distance to the base of the shape (GB) [7].”
Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts (2020, background): “e Contexts. We hope to integrate spatial contexts into the pre-training objective. There are many ways to achieve the goal, and here we take inspiration from the classic ShapeContext local descriptor [4,35,67] for shape matching. The ShapeContext descriptor partitions the space into spatially inhomo”
A Robust 3D-2D Interactive Tool for Scene Segmentation and Annotation (2016, background): “ape context. The shape context descriptor is endowed with scaleinvariant by normalizing ku ijkby the mean of the lengths of all vectors. To make the shape context rotation invariant, 6 Kortgen et al. [39] computed the spherical coordinates (;˚) ij relatively to the eigenvectors of the covariance mat”
Intrinsic shape context descriptors for deformable shapes (2012, background): “3D Shape contexts were explored earlier in [24, 15]; but these works are not intrinsic, i.e. surface deformations affect the descriptors.”
Robust 3D Shape Correspondence in the Spectral Domain (2006, methodology): “These methods have subsequently been generalized in a straightforward manner to handle 3D point sets [18].”
Attentional ShapeContextNet for Point Cloud Recognition (2018, methodology): “Similar to [18], we use concentric shells to design the shape context kernel.”
Three-dimensional shape searching: state-of-the-art review and future trends (2005, unknown): “[125], where shapes are matched using 3D shape contexts.”
Sliding Shapes for 3D Object Detection in Depth Images (2014, unknown): “Keypoint matching: Just as SIFT keypoints for image matching [50], a popular type of algorithms [51–60] is to detect keypoints on a 3D point cloud or a mesh, generate descriptors for the keypoints (e.”
A survey of content based 3D shape retrieval methods (2004, methodology): “[45] apply 3D shape contexts for 3D shape retrieval and matching.”
Geometric Back-Projection Network for Point Cloud Classification (2019, background): “, shape context [44], point histograms [17], etc.”
Bio-inspired Dynamic 3D Discriminative Skeletal Features for Human Action Recognition (2013, unknown): “The subspace angles, {θ i } n i=1 can then be computed as θ i = cos −1 (λ i ).”