Abstract | ||
---|---|---|
Currently, in Autonomous Driving (AD), most of the 3D object detection frameworks (either anchor- or anchor-free-based) consider the detection as a Bounding Box (BBox) regression problem. However, this compact representation is not sufficient to explore all the information of the objects. To tackle this problem, we propose a simple but practical detection framework to jointly predict the 3D BBox and instance segmentation. For instance segmentation, we propose a Spatial Embeddings (SEs) strategy to assemble all foreground points into their corresponding object centers. Base on the SE results, the object proposals can be generated based on a simple clustering strategy. For each cluster, only one proposal is generated. Therefore, the Non-Maximum Suppression (NMS) process is no longer needed here. Finally, with our proposed instance-aware ROI pooling, the BBox is refined by a second-stage network. Experimental results on the public KITTI dataset show that the proposed SEs can significantly improve the instance segmentation results compared with other feature embedding-based method. Meanwhile, it also outperforms most of the 3D object detectors on the KITTI testing benchmark. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/CVPR42600.2020.00191 | 2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) |
DocType | ISSN | Citations |
Conference | 1063-6919 | 0 |
PageRank | References | Authors |
0.34 | 32 | 8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Dingfu Zhou | 1 | 86 | 11.23 |
Jin Fang | 2 | 28 | 7.66 |
Xibin Song | 3 | 121 | 8.84 |
Liu Liu | 4 | 16 | 3.64 |
Junbo Yin | 5 | 13 | 3.91 |
Yuchao Dai | 6 | 418 | 42.03 |
Hongdong Li | 7 | 1724 | 101.81 |
Ruigang Yang | 8 | 3675 | 226.03 |