IEEE Transactions on Pattern Analysis and Machine Intelligence · 1997 · 151 citations · 18 references
ComputingComputer ScienceComputational GeometryComputer VisionMachine Vision3D ReconstructionGeometry ProcessingMulti-view GeometryRobotic VisionScene UnderstandingSurface ReconstructionGeometric ReconstructionNoise-robust ReconstructionObject ReconstructionRange Image Reconstruction
We present an approach to reliable and efficient recovery of part-descriptions in terms of superquadric models from range data. We show that superquadrics can directly be recovered from unsegmented data, thus avoiding any presegmentation steps (e.g. in terms of surfaces). The approach is based on the recover-and-select paradigm. We present several experiments on real and synthetic range images, where we demonstrate the stability of the results with respect to viewpoint and noise.
18
Neural networks for optimization and signal processing
Adam Krzyżak · Neurocomputing · 1994 · 1.2K citations
Neural networks for optimization and signal processing
Choice Reviews Online · 1993 · 1.2K citations
Superquadrics and Angle-Preserving Transformations
Barr · IEEE Computer Graphics and Applications · 1981 · 1.1K citations