Corpus ID: 232168876

Offboard 3D Object Detection from Point Cloud Sequences

@article{Qi2021Offboard3O,
  title={Offboard 3D Object Detection from Point Cloud Sequences},
  author={C. Qi and Y. Zhou and Mahyar Najibi and Pei Sun and Khoa T. Vo and Boyang Deng and Dragomir Anguelov},
  journal={ArXiv},
  year={2021},
  volume={abs/2103.05073}
}
While current 3D object recognition research mostly focuses on the real-time, onboard scenario, there are many offboard use cases of perception that are largely underexplored, such as using machines to automatically generate high-quality 3D labels. Existing 3D object detectors fail to satisfy the high-quality requirement for offboard uses due to the limited input and speed constraints. In this paper, we propose a novel offboard 3D object detection pipeline using point cloud sequence data… Expand
1 Citations
Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset

References

SHOWING 1-10 OF 79 REFERENCES
What You See is What You Get: Exploiting Visibility for 3D Object Detection
PointPillars: Fast Encoders for Object Detection From Point Clouds
Scalability in Perception for Autonomous Driving: Waymo Open Dataset
3DSSD: Point-Based 3D Single Stage Object Detector
4d forecasting: Sequential forecasting
  • 2020
AFDet: Anchor Free One Stage 3D Object Detection
An LSTM Approach to Temporal 3D Object Detection in LiDAR Point Clouds
Autolabeling 3D Objects With Differentiable Rendering of SDF Shape Priors
HVNet: Hybrid Voxel Network for LiDAR Based 3D Object Detection
...
1
2
3
4
5
...