InfoFocus: 3D Object Detection for Autonomous Driving with Dynamic Information Modeling
This work addresses a key challenge in real-time 3D object detection for autonomous cars, offering an incremental improvement over existing voxel-based methods.
The paper tackles the problem of non-uniform point cloud distribution in 3D object detection for autonomous driving by proposing InfoFocus, a framework that dynamically refines features based on point cloud density, achieving state-of-the-art performance with 31 FPS and a 9.0% mAP improvement on the nuScenes benchmark.
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.