· 2019
PointRCNN: 3D Object Proposal Generation and Detection From Point Cloud
- 2,977citations
- 2019year
Short summary
PointRCNN introduces a novel two-stage framework that directly generates 3D object proposals from raw point clouds, bypassing the need for RGB images or intermediate representations like bird's-eye view or voxels.
AI-generated from the title and abstract; the full text is not read.
Key points
- Directly generates 3D object proposals from raw point clouds, unlike prior methods using RGB images or intermediate representations.
- A two-stage framework: bottom-up proposal generation via foreground segmentation, followed by proposal refinement.
- Stage-2 refines proposals using canonical coordinates and combines local spatial features with global semantic features from stage-1.
- Achieves state-of-the-art performance on the KITTI 3D detection benchmark using only point cloud input.
AI-generated from the title and abstract; the full text is not read.
Abstract
In this paper, we propose PointRCNN for 3D object detection from raw point cloud. The whole framework is composed of two stages: stage-1 for the bottom-up 3D proposal generation and stage-2 for refining proposals in the canonical coordinates to obtain the final detection results. Instead of generating proposals from RGB image or projecting point cloud to bird's view or voxels as previous methods do, our stage-1 sub-network directly generates a small number of high-quality 3D proposals from point cloud in a bottom-up manner via segmenting the point cloud of the whole scene into foreground points and background. The stage-2 sub-network transforms the pooled points of each proposal to canonical coordinates to learn better local spatial features, which is combined with global semantic features of each point learned in stage-1 for accurate box refinement and confidence prediction. Extensive experiments on the 3D detection benchmark of KITTI dataset show that our proposed architecture outperforms state-of-the-art methods with remarkable margins by using only point cloud as input. The code is available at https://github.com/sshaoshuai/PointRCNN.
The authors' abstract, as published at the source., 2019 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Computational Mechanics
Computational MechanicsEngineering