A-CNN: Annularly Convolutional Neural Networks on Point Clouds
This addresses the problem of 3D point cloud analysis for computer vision applications, offering a novel method for handling geometric variability, though it appears incremental in improving convolution techniques.
The paper tackles the challenge of analyzing 3D point clouds due to irregularity and sparsity by introducing annular convolution, a new operator that captures local geometry using ring-shaped structures, and demonstrates that it outperforms state-of-the-art methods on standard benchmarks like ModelNet10 and S3DIS.
Analyzing the geometric and semantic properties of 3D point clouds through the deep networks is still challenging due to the irregularity and sparsity of samplings of their geometric structures. This paper presents a new method to define and compute convolution directly on 3D point clouds by the proposed annular convolution. This new convolution operator can better capture the local neighborhood geometry of each point by specifying the (regular and dilated) ring-shaped structures and directions in the computation. It can adapt to the geometric variability and scalability at the signal processing level. We apply it to the developed hierarchical neural networks for object classification, part segmentation, and semantic segmentation in large-scale scenes. The extensive experiments and comparisons demonstrate that our approach outperforms the state-of-the-art methods on a variety of standard benchmark datasets (e.g., ModelNet10, ModelNet40, ShapeNet-part, S3DIS, and ScanNet).