Dense-Resolution Network for Point Cloud Classification and Segmentation

TL;DR

This paper introduces Dense-Resolution Network (DRNet), a novel architecture for point cloud classification and segmentation that effectively captures local features at multiple resolutions, outperforming existing methods on standard benchmarks.

Contribution

The paper proposes a new network with a novel grouping method and error-minimizing module for improved local feature learning in point cloud analysis.

Findings

Superior performance on ModelNet40, ShapeNet, and ScanObjectNN datasets.

Effective local feature learning through novel grouping and error-minimizing modules.

Validated components through visualization and benchmarking.

Abstract

Point cloud analysis is attracting attention from Artificial Intelligence research since it can be widely used in applications such as robotics, Augmented Reality, self-driving. However, it is always challenging due to irregularities, unorderedness, and sparsity. In this article, we propose a novel network named Dense-Resolution Network (DRNet) for point cloud analysis. Our DRNet is designed to learn local point features from the point cloud in different resolutions. In order to learn local point groups more effectively, we present a novel grouping method for local neighborhood searching and an error-minimizing module for capturing local features. In addition to validating the network on widely used point cloud segmentation and classification benchmarks, we also test and visualize the performance of the components. Comparing with other state-of-the-art methods, our network shows superiority on ModelNet40, ShapeNet synthetic and ScanObjectNN real point cloud datasets.