PolarFormer: Multi-Camera 3D Object Detection with Polar Transformer
Fudan University · University of Chinese Academy of Sciences · +3 more institutions
Abstract
3D object detection in autonomous driving aims to reason “what” and “where” the objects of interest present in a 3D world. Following the conventional wisdom of previous 2D object detection, existing methods often adopt the canonical Cartesian coordinate system with perpendicular axis. However, we conjugate that this does not fit the nature of the ego car’s perspective, as each onboard camera perceives the world in shape of wedge intrinsic to the imaging geometry with radical (non perpendicular) axis. Hence, in this paper we advocate the exploitation of the Polar coordinate system and propose a new Polar Transformer (PolarFormer) for more accurate 3D object detection in the bird’s-eye-view (BEV) taking as input…
Citation impact
- FWCI
- 10.14
- Percentile
- 100%
- References
- 63
Authors
7Topics & keywords
- Computer vision
- Artificial intelligence
- Cartesian coordinate system
- Computer science
- Polar coordinate system
- Polar
- Object detection
- Coordinate system
Funding
- NSNatural Science Foundation of ShanghaiAward: 22ZR1407500
- NNNational Natural Science Foundation of ChinaAwards: 2018KZDXM066, 62192782, 2017KZDXM081, 61972394, 62036011, U22B2056, 6210020439, 61721004, 62102417
- YIYouth Innovation Promotion Association of the Chinese Academy of SciencesAward: 202202
- YIYouth Innovation Promotion Association