3DSSD: Point-based 3D Single Stage Object Detector
| Autor: | Yanan Sun, Jiaya Jia, Zetong Yang, Shu Liu |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
0209 industrial biotechnology Computer science business.industry Computer Vision and Pattern Recognition (cs.CV) Detector Feature extraction Process (computing) Computer Science - Computer Vision and Pattern Recognition Sampling (statistics) 02 engineering and technology Object detection Upsampling 020901 industrial engineering & automation Margin (machine learning) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Point (geometry) Computer vision Artificial intelligence business |
| Zdroj: | CVPR |
| Popis: | Currently, there have been many kinds of voxel-based 3D single stage detectors, while point-based single stage methods are still underexplored. In this paper, we first present a lightweight and effective point-based 3D single stage object detector, named 3DSSD, achieving a good balance between accuracy and efficiency. In this paradigm, all upsampling layers and refinement stage, which are indispensable in all existing point-based methods, are abandoned to reduce the large computation cost. We novelly propose a fusion sampling strategy in downsampling process to make detection on less representative points feasible. A delicate box prediction network including a candidate generation layer, an anchor-free regression head with a 3D center-ness assignment strategy is designed to meet with our demand of accuracy and speed. Our paradigm is an elegant single stage anchor-free framework, showing great superiority to other existing methods. We evaluate 3DSSD on widely used KITTI dataset and more challenging nuScenes dataset. Our method outperforms all state-of-the-art voxel-based single stage methods by a large margin, and has comparable performance to two stage point-based methods as well, with inference speed more than 25 FPS, 2x faster than former state-of-the-art point-based methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|