ModelNet-O: A Large-Scale Synthetic Dataset for Occlusion-Aware Point Cloud Classification
This addresses the limitation of current point cloud datasets for occlusion-aware classification, which is crucial for practical applications like robotics and autonomous driving, though it is incremental as it builds on existing methods.
The authors tackled the problem of occlusion in 3D point cloud classification by introducing ModelNet-O, a large-scale synthetic dataset with 123,041 samples that is 10 times larger than existing datasets, and proposed PointMLS, which achieved state-of-the-art results on this dataset.
Recently, 3D point cloud classification has made significant progress with the help of many datasets. However, these datasets do not reflect the incomplete nature of real-world point clouds caused by occlusion, which limits the practical application of current methods. To bridge this gap, we propose ModelNet-O, a large-scale synthetic dataset of 123,041 samples that emulate real-world point clouds with self-occlusion caused by scanning from monocular cameras. ModelNet-O is 10 times larger than existing datasets and offers more challenging cases to evaluate the robustness of existing methods. Our observation on ModelNet-O reveals that well-designed sparse structures can preserve structural information of point clouds under occlusion, motivating us to propose a robust point cloud processing method that leverages a critical point sampling (CPS) strategy in a multi-level manner. We term our method PointMLS. Through extensive experiments, we demonstrate that our PointMLS achieves state-of-the-art results on ModelNet-O and competitive results on regular datasets, and it is robust and effective. More experiments also demonstrate the robustness and effectiveness of PointMLS.