GeoSegNet: Point Cloud Semantic Segmentation via Geometric Encoder-Decoder Modeling
Semantic segmentation of point clouds, aiming to assign each point a semantic category, is critical to 3D scene understanding.Despite of significant advances in recent years, most of existing methods still suffer from either the object-level misclassification or the boundary-level ambiguity. In this paper, we present a robust semantic segmentation network by deeply exploring the geometry of point clouds, dubbed GeoSegNet. Our GeoSegNet consists of a multi-geometry based encoder and a boundary-guided decoder. In the encoder, we develop a new residual geometry module from multi-geometry perspectives to extract object-level features. In the decoder, we introduce a contrastive boundary learning module to enhance the geometric representation of boundary points. Benefiting from the geometric encoder-decoder modeling, our GeoSegNet can infer the segmentation of objects effectively while making the intersections (boundaries) of two or more objects clear. Experiments show obvious improvements of our method over its competitors in terms of the overall segmentation accuracy and object boundary clearness. Code is available at https://github.com/Chen-yuiyui/GeoSegNet.
Code (1)
Tasks
DecoderObjectSegmentationSemantic SegmentationSimilar Papers 제목 키워드 기반
GFNet: Geometric Flow Network for 3D Point Cloud Semantic Segmentation
Point cloud semantic segmentation from projected views, such as range-view (RV) and bird's-eye-view (BEV), has been intensively investigated. Different views capture different information of point clouds and thus are com…
3D Semantic SegmentationLIDAR Semantic SegmentationRepresentation LearningRobust 3D Semantic Segmentation+2Domain-aware Category-level Geometry Learning Segmentation for 3D Point Clouds
Domain generalization in 3D segmentation is a critical challenge in deploying models to unseen environments. Current methods mitigate the domain shift by augmenting the data distribution of point clouds. However, the mod…
3D Semantic SegmentationDomain GeneralizationPoint CloudsAugmented Semantic Signatures of Airborne LiDAR Point Clouds for Comparison
LiDAR point clouds provide rich geometric information, which is particularly useful for the analysis of complex scenes of urban regions. Finding structural and semantic differences between two different three-dimensional…
Geometrically-driven Aggregation for Zero-shot 3D Point Cloud Understanding
Zero-shot 3D point cloud understanding can be achieved via 2D Vision-Language Models (VLMs). Existing strategies directly map Vision-Language Models from 2D pixels of rendered or captured views to 3D points, overlooking …
SegmentationSemantic SegmentationGeometric-Aware Hypergraph Reasoning for Novel Class Discovery in Point Cloud Segmentation
Novel class discovery in point cloud segmentation aims to transfer knowledge from known classes to automatically identify and segment unlabeled novel classes in point clouds. Existing methods mainly rely on pairwise asso…
Point Cloud SegmentationNovel Class DiscoverySemantic SegmentationPoint Clouds