Dense-Resolution Network for Point Cloud Classification and Segmentation

14 May 2020  ·  Shi Qiu, Saeed Anwar, Nick Barnes ·

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.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
3D Point Cloud Classification ModelNet40 DRNet Overall Accuracy 93.1 # 59
3D Point Cloud Classification ScanObjectNN DRNet Overall Accuracy 80.3 # 51
Mean Accuracy 78.0 # 22
3D Part Segmentation ShapeNet-Part DRNet Class Average IoU 83.7 # 17
Instance Average IoU 86.4 # 22


No methods listed for this paper. Add relevant methods here