IPD-Net: SO(3) Invariant Primitive Decompositional Network for 3D Point Clouds

Ramesh Ashok Tabib, Nitishkumar Upasi, Tejas Anvekar, Dikshit Hegde, Uma Mudenagudi; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2023, pp. 2736-2744

In this paper, we propose IPD-Net: Invariant Primitive Decompositional Network, a SO(3) invariant framework for decomposition of a point cloud. The human cognitive system is able to identify and interpret familiar objects regardless of their orientation and abstraction. Recent research aims to bring this capability to machines for understanding the 3D world. In this work, we present a framework inspired by human cognition to decompose point clouds into four primitive 3D shapes (plane, cylinder, cone, and sphere) and enable machines to understand the objects in various orientations. We employ Implicit Invariant Features (IIF) to learn local geometric relations by implicitly representing the point cloud with enhanced geometric information invariant towards SO(3) rotations. We also use Spatial Rectification Unit (SRU) to extract invariant global signatures. We demonstrate the results of our proposed methodology for SO(3) invariant decomposition on TraceParts Dataset, and show the generalizability of proposed IPD-Net as plugin for downstream task on classification of point clouds. We compare the results of classification with state-of-the-art methods on benchmark dataset (ModelNet40).