SceneEncoder: Scene-Aware Semantic Segmentation of Point Clouds with A Learnable Scene Descriptor
This work addresses the challenge of effectively using global information for point cloud semantic segmentation, which is important for applications like robotics and autonomous driving, but it is incremental as it builds on existing networks.
The paper tackles the problem of semantic segmentation of point clouds by introducing a SceneEncoder module that learns a scene descriptor to filter out irrelevant object categories, and a region similarity loss to reduce local segmentation noise. The method improves baseline performance and achieves state-of-the-art results on ScanNet and ShapeNet datasets.
Besides local features, global information plays an essential role in semantic segmentation, while recent works usually fail to explicitly extract the meaningful global information and make full use of it. In this paper, we propose a SceneEncoder module to impose a scene-aware guidance to enhance the effect of global information. The module predicts a scene descriptor, which learns to represent the categories of objects existing in the scene and directly guides the point-level semantic segmentation through filtering out categories not belonging to this scene. Additionally, to alleviate segmentation noise in local region, we design a region similarity loss to propagate distinguishing features to their own neighboring points with the same label, leading to the enhancement of the distinguishing ability of point-wise features. We integrate our methods into several prevailing networks and conduct extensive experiments on benchmark datasets ScanNet and ShapeNet. Results show that our methods greatly improve the performance of baselines and achieve state-of-the-art performance.