arXiv (Cornell University) · 2017 · 25 citations · 40 references
ComputingComputer ScienceComputational GeometryComputer VisionOptimization3D ReconstructionGeometry ProcessingKernel MethodsShape AnalysisShape DeformationShape RepresentationConvex FunctionsCorrespondence ProblemDescent OptimizationDescriptor MatchingKernel MatchingKernel-based MatchingShape CorrespondenceShape Matching
We present a method to match three dimensional shapes under non-isometric deformations, topology changes and partiality. We formulate the problem as matching between a set of pair-wise and point-wise descriptors, imposing a continuity prior on the mapping, and propose a projected descent optimization procedure inspired by difference of convex functions (DC) programming. Surprisingly, in spite of the highly non-convex nature of the resulting quadratic assignment problem, our method converges to a semantically meaningful and continuous mapping in most of our experiments, and scales well. We provide preliminary theoretical analysis and several interpretations of the method.
40
Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs
Federico Monti, Davide Boscaini, Jonathan Masci et al. · 2017 · 1.9K citations
Dragomir Anguelov, Daphne Koller, Sebastian Thrun et al. · ACM Transactions on Graphics · 2005 · 1.6K citations