Multi-kernel diffusion CNNs for graph-based learning on point clouds

Lasse Hansen*, Jasper Diesel, Mattias P. Heinrich

*Corresponding author for this work


Graph convolutional networks are a new promising learning approach to deal with data on irregular domains. They are predestined to overcome certain limitations of conventional grid-based architectures and will enable efficient handling of point clouds or related graphical data representations, e.g. superpixel graphs. Learning feature extractors and classifiers on 3D point clouds is still an underdeveloped area and has potential restrictions to equal graph topologies. In this work, we derive a new architectural design that combines rotationally and topologically invariant graph diffusion operators and node-wise feature learning through $$1\times 1$$ convolutions. By combining multiple isotropic diffusion operations based on the Laplace-Beltrami operator, we can learn an optimal linear combination of diffusion kernels for effective feature propagation across nodes on an irregular graph. We validated our approach for learning point descriptors as well as semantic classification on real 3D point clouds of human poses and demonstrate an improvement from 85% to 95% in Dice overlap with our multi-kernel approach.

Original languageEnglish
Title of host publicationECCV 2018: Computer Vision – ECCV 2018 Workshops
EditorsLaura Leal-Taixé, Stefan Roth
Number of pages14
Volume11131 LNCS
PublisherSpringer, Cham
Publication date23.01.2019
ISBN (Print)978-3-030-11014-7
ISBN (Electronic)978-3-030-11015-4
Publication statusPublished - 23.01.2019
Event15th European Conference on Computer Vision - Munich, Germany
Duration: 08.09.201814.09.2018


Dive into the research topics of 'Multi-kernel diffusion CNNs for graph-based learning on point clouds'. Together they form a unique fingerprint.

Cite this