3D-BEVIS: Bird's-Eye-View Instance Segmentation

3 Apr 2019  ·  Cathrin Elich, Francis Engelmann, Theodora Kontogianni, Bastian Leibe ·

Recent deep learning models achieve impressive results on 3D scene analysis tasks by operating directly on unstructured point clouds. A lot of progress was made in the field of object classification and semantic segmentation. However, the task of instance segmentation is less explored. In this work, we present 3D-BEVIS, a deep learning framework for 3D semantic instance segmentation on point clouds. Following the idea of previous proposal-free instance segmentation approaches, our model learns a feature embedding and groups the obtained feature space into semantic instances. Current point-based methods scale linearly with the number of points by processing local sub-parts of a scene individually. However, to perform instance segmentation by clustering, globally consistent features are required. Therefore, we propose to combine local point geometry with global context information from an intermediate bird's-eye view representation.

PDF Abstract


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
3D Semantic Instance Segmentation ScanNetV2 3D-BEVIS mAP@0.50 24.8 # 4


No methods listed for this paper. Add relevant methods here