Investigate Indistinguishable Points in Semantic Segmentation of 3D Point Cloud
This addresses performance issues in 3D semantic segmentation for applications like robotics or autonomous driving, but it is incremental as it builds on existing methods with a focus on specific challenging points.
The paper tackles the problem of indistinguishable points in 3D point cloud semantic segmentation, which harm performance, by proposing IAF-Net to adaptively select and enhance features for these points, achieving comparable state-of-the-art results on datasets like S3DIS and ScanNet and outperforming others on a new IPBM metric.
This paper investigates the indistinguishable points (difficult to predict label) in semantic segmentation for large-scale 3D point clouds. The indistinguishable points consist of those located in complex boundary, points with similar local textures but different categories, and points in isolate small hard areas, which largely harm the performance of 3D semantic segmentation. To address this challenge, we propose a novel Indistinguishable Area Focalization Network (IAF-Net), which selects indistinguishable points adaptively by utilizing the hierarchical semantic features and enhances fine-grained features for points especially those indistinguishable points. We also introduce multi-stage loss to improve the feature representation in a progressive way. Moreover, in order to analyze the segmentation performances of indistinguishable areas, we propose a new evaluation metric called Indistinguishable Points Based Metric (IPBM). Our IAF-Net achieves the comparable results with state-of-the-art performance on several popular 3D point cloud datasets e.g. S3DIS and ScanNet, and clearly outperforms other methods on IPBM.