Related papers: RangeRCNN: Towards Fast and Accurate 3D Object Det…

Effective BEV object detection on infrastructure can greatly improve traffic scenes understanding and vehicle-toinfrastructure (V2I) cooperative perception. However, cameras installed on infrastructure have various postures, and previous…

In recent years 3D object detection from LiDAR point clouds has made great progress thanks to the development of deep learning technologies. Although voxel or point based methods are popular in 3D object detection, they usually involve…

Simultaneous perception of 2D objects in perspective view and 3D objects in Bird's Eye View (BEV) is challenging for multi-camera autonomous driving. Existing two-stage pipelines use 2D results only as a one-time cue for 3D detection. We…

LiDAR-based 3D object detection plays a crucial role in modern autonomous driving systems. LiDAR data often exhibit severe changes in properties across different observation ranges. In this paper, we explore cross-range adaptation for 3D…

Most current detection methods have adopted anchor boxes as regression references. However, the detection performance is sensitive to the setting of the anchor boxes. A proper setting of anchor boxes may vary significantly across different…

Efficiently and completely capturing the three-dimensional data of an object is a fundamental problem in industrial and robotic applications. The task of next-best-view (NBV) planning is to infer the pose of the next viewpoint based on the…

In this paper, we propose PointRCNN for 3D object detection from raw point cloud. The whole framework is composed of two stages: stage-1 for the bottom-up 3D proposal generation and stage-2 for refining proposals in the canonical…

We present Point-Voxel CNN (PVCNN) for efficient, fast 3D deep learning. Previous work processes 3D data using either voxel-based or point-based NN models. However, both approaches are computationally inefficient. The computation cost and…

High-quality 3D object recognition is an important component of many vision and robotics systems. We tackle the object recognition problem using two data representations, to achieve leading results on the Princeton ModelNet challenge. The…

Current state-of-the-art two-stage detectors generate oriented proposals through time-consuming schemes. This diminishes the detectors' speed, thereby becoming the computational bottleneck in advanced oriented object detection systems. This…

Current neural networks-based object detection approaches processing LiDAR point clouds are generally trained from one kind of LiDAR sensors. However, their performances decrease when they are tested with data coming from a different LiDAR…

3D object detection at long range is crucial for ensuring the safety and efficiency of self driving vehicles, allowing them to accurately perceive and react to objects, obstacles, and potential hazards from a distance. But most current…

Recently, 3D object detection algorithms based on radar and camera fusion have shown excellent performance, setting the stage for their application in autonomous driving perception tasks. Existing methods have focused on dealing with…

We present a unified, efficient and effective framework for point-cloud based 3D object detection. Our two-stage approach utilizes both voxel representation and raw point cloud data to exploit respective advantages. The first stage network,…

Accurate 3D lane detection from monocular images presents significant challenges due to depth ambiguity and imperfect ground modeling. Previous attempts to model the ground have often used a planar ground assumption with limited degrees of…

Collaborative perception is dedicated to tackling the constraints of single-agent perception, such as occlusions, based on the multiple agents' multi-view sensor inputs. However, most existing works assume an ideal condition that all…

We propose Shift R-CNN, a hybrid model for monocular 3D object detection, which combines deep learning with the power of geometry. We adapt a Faster R-CNN network for regressing initial 2D and 3D object properties and combine it with a…

Next Best View (NBV) algorithms aim to maximize 3D scene acquisition quality using minimal resources, e.g. number of acquisitions, time taken, or distance traversed. Prior methods often rely on coverage maximization as a proxy for…

Object detection is a fundamental and challenging problem in aerial and satellite image analysis. More recently, a two-stage detector Faster R-CNN is proposed and demonstrated to be a promising tool for object detection in optical remote…

R-CNN style methods are sorts of the state-of-the-art object detection methods, which consist of region proposal generation and deep CNN classification. However, the proposal generation phase in this paradigm is usually time consuming,…