3D-MPA: Multi-Proposal Aggregation for 3D Semantic Instance Segmentation
Authors:
- 1 June 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 9028-9037
Abstract
We present 3D-MPA, a method for instance segmentation on 3D point clouds. Given an input point cloud, we propose an object-centric approach where each point votes for its object center. We sample object proposals from the predicted object centers. Then, we learn proposal features from grouped point features that voted for the same object center. A graph convolutional network introduces inter-proposal relations, providing higher-level feature learning in addition to the lower-level point features. Each proposal comprises a semantic label, a set of associated points over which we define a foreground-background mask, an objectness score and aggregation features. Previous works usually perform non-maximum-suppression (NMS) over proposals to obtain the final object detections or semantic instances. However, NMS can discard potentially correct predictions. Instead, our approach keeps all proposals and groups them together based on the learned aggregation features. We show that grouping proposals improves over NMS and outperforms previous state-of-the-art methods on the tasks of 3D object detection and semantic instance segmentation on the ScanNetV2 benchmark and the S3DIS dataset.Keywords
All Related Versions
This publication has 34 references indexed in Scilit:
- 3D Graph Neural Networks for RGBD Semantic Segmentation2017
- Focal Loss for Dense Object Detection2017
- Mask R-CNN2017
- ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes2017
- BundleFusionACM Transactions on Graphics, 2017
- Volumetric and Multi-view CNNs for Object Classification on 3D Data2016
- Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Images2016
- 3D Semantic Parsing of Large-Scale Indoor Spaces2016
- ElasticFusion: Dense SLAM Without A Pose Graph2015
- Real-time 3D reconstruction at scale using voxel hashingACM Transactions on Graphics, 2013