Abstract | ||
---|---|---|
The backbone network adopted in state-of-the-art 3D object detectors lacks a good balance between high point resolution and large receptive field, both of which are desirable for object detection on point clouds. This work proposes Dense Point Diffusion module, a novel backbone network that solves these issues. It adopts dilated point convolution as a building block to enlarge the receptive field and retain the point resolution at the same time. Further, a number of such layers are densely connected, giving rise to large receptive field and multi-scale feature fusion, which are effective for object detection task. Comprehensive experiments verify the efficacy of our approach. The source code
<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup>
has been released to facilitate the reproduction of the results. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/3DV50981.2020.00086 | 2020 International Conference on 3D Vision (3DV) |
Keywords | DocType | ISSN |
receptive field,multiscale feature fusion,object detection task,state-of-the-art 3D object detectors,high point resolution,point clouds,backbone network,point convolution,dense point diffusion module | Conference | 2378-3826 |
ISBN | Citations | PageRank |
978-1-7281-8129-5 | 0 | 0.34 |
References | Authors | |
0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
X.L. Liu | 1 | 11 | 11.83 |
Jiayan Cao | 2 | 0 | 0.34 |
Qianqian Bi | 3 | 0 | 0.34 |
Jian Wang | 4 | 18 | 2.07 |
Boxin Shi | 5 | 0 | 0.68 |
Yichen Wei | 6 | 0 | 0.34 |