-
3D Backbone Network for 3D Object Detection
The task of detecting 3D objects in point cloud has a pivotal role in ma...
read it
-
IPOD: Intensive Point-based Object Detector for Point Cloud
We present a novel 3D object detection framework, named IPOD, based on r...
read it
-
Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection
Recent advances on 3D object detection heavily rely on how the 3D data a...
read it
-
Fast Point R-CNN
We present a unified, efficient and effective framework for point-cloud ...
read it
-
Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection
This report presents our method which wins the nuScenes3D Detection Chal...
read it
-
Fast Hybrid Cascade for Voxel-based 3D Object Classification
Voxel-based 3D object classification has been frequently studied in rece...
read it
-
Patch Refinement – Localized 3D Object Detection
We introduce Patch Refinement a two-stage model for accurate 3D object d...
read it
InfoFocus: 3D Object Detection for Autonomous Driving with Dynamic Information Modeling
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
READ FULL TEXT
Comments
There are no comments yet.