Litcius/Paper detail

Dynamic Local Geometry Capture in 3D Point Cloud Classification

Shivanand Venkanna Sheshappanavar, Chandra Kambhamettu

202114 citationsDOI

Abstract

With the advent of PointNet, the popularity of deep neural networks has increased in point cloud analysis. PointNet’s successor, PointNet++, partitions the input point cloud and recursively applies PointNet to capture local geometry. PointNet++ model uses ball querying for local geometry capture in its set abstraction layers. Several models based on single scale grouping of PointNet++ continue to use ball querying with a fixed-radius ball. Due to its uniform scale in all directions, a ball lacks orientation and is ineffective in capturing complex local neighborhoods. Few recent models replace a fixed-sized ball with a fixed-sized ellipsoid or a fixed-sized cuboid to capture local neighborhoods. However, these methods are not still fully effective in capturing varying geometry proportions from different local neighborhoods on the object surface. We propose a novel technique of dynamically oriented and scaled ellipsoid based on unique local information to capture the local geometry better. We also propose ReducedPointNet++, a single set abstraction based single scale grouping model. Our model, along with dynamically oriented and scaled ellipsoid querying, achieves 92.1% classification accuracy on the ModelNet40 dataset. We achieve state-of-the-art 3D classification results on all six variants of the real-world ScanObjectNN dataset with an accuracy of 82.0% on the most challenging variant.

Topics & Concepts

Point cloudComputer scienceEllipsoidBall (mathematics)Artificial intelligenceAbstractionEuclidean geometryGeometryMathematicsGeographyPhilosophyGeodesyEpistemology3D Shape Modeling and Analysis3D Surveying and Cultural HeritageComputer Graphics and Visualization Techniques
Dynamic Local Geometry Capture in 3D Point Cloud Classification | Litcius