Anchor-free 3D single stage detector with mask-guided attention for point cloud

Document Type

Conference Proceeding

Publication Title

MM 2021 - Proceedings of the 29th ACM International Conference on Multimedia

Abstract

Most of the existing single-stage and two-stage 3D object detectors are anchor-based methods, while the efficient but challenging anchor-free single-stage 3D object detection is not well investigated. Recent studies on 2D object detection show that the anchor-free methods also are of great potential. However, the unordered and sparse properties of point clouds prevent us from directly leveraging the advanced 2D methods on 3D point clouds. We overcome this by converting the voxel-based sparse 3D feature volumes into the sparse 2D feature maps. We propose an attentive module to fit the sparse feature maps to dense mostly on the object regions through the deformable convolution tower and the supervised mask-guided attention. By directly regressing the 3D bounding box from the enhanced and dense feature maps, we construct a novel single-stage 3D detector for point clouds in an anchor-free manner. We propose an IoU-based detection confidence re-calibration scheme to improve the correlation between the detection confidence score and the accuracy of the bounding box regression. Our code is publicly available at https://github.com/jialeli1/MGAF-3DSSD.

First Page

553

Last Page

562

DOI

10.1145/3474085.3475208

Publication Date

10-17-2021

Keywords

3D object detection, anchor-free, point cloud, single stage

Comments

IR Deposit conditions: non-described

Link to Full Text

Share

COinS