3DSSD

2000년 도입 · 논문 1편에서 사용

3DSSD is a point-based 3D single stage object detection detector. 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. The authors propose a fusion sampling strategy in the 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 the needs of accuracy and speed.

출처: 3DSSD: Point-based 3D Single Stage Object Detector

소개 논문: 3DSSD: Point-based 3D Single Stage Object Detector