InfoFocus: 3D Object Detection for Autonomous Driving with Dynamic Information Modeling

ECCV 2020  ·  Jun Wang, Shiyi Lan, Mingfei Gao, Larry S. Davis ·

Real-time 3D object detection is crucial for autonomous cars. Achieving promising performance with high efficiency, voxel-based approaches have received considerable attention. However, previous methods model the input space with features extracted from equally divided sub-regions without considering that point cloud is generally non-uniformly distributed over the space. To address this issue, we propose a novel 3D object detection framework with dynamic information modeling. The proposed framework is designed in a coarse-to-fine manner. Coarse predictions are generated in the first stage via a voxel-based region proposal network. We introduce InfoFocus, which improves the coarse detections by adaptively refining features guided by the information of point cloud density. Experiments are conducted on the large-scale nuScenes 3D detection benchmark. Results show that our framework achieves the state-of-the-art performance with 31 FPS and improves our baseline significantly by 9.0% mAP on the nuScenes test set.

PDF Abstract ECCV 2020 PDF ECCV 2020 Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
3D Object Detection nuScenes InfoFocus NDS 0.4 # 328
mAP 0.39 # 289
mATE 0.36 # 198
mASE 0.26 # 47
mAOE 1.13 # 13
mAVE 1.0 # 58
mAAE 0.4 # 29

Methods


No methods listed for this paper. Add relevant methods here