CVFNet: Real-time 3D Object Detection by Learning Cross View Features

by   Jiaqi Gu, et al.

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 time-consuming operations such as 3D convolutions on voxels or ball query among points, making the resulting network inappropriate for time critical applications. On the other hand, 2D view-based methods feature high computing efficiency while usually obtaining inferior performance than the voxel or point based methods. In this work, we present a real-time view-based single stage 3D object detector, namely CVFNet to fulfill this task. To strengthen the cross-view feature learning under the condition of demanding efficiency, our framework extracts the features of different views and fuses them in an efficient progressive way. We first propose a novel Point-Range feature fusion module that deeply integrates point and range view features in multiple stages. Then, a special Slice Pillar is designed to well maintain the 3D geometry when transforming the obtained deep point-view features into bird's eye view. To better balance the ratio of samples, a sparse pillar detection head is presented to focus the detection on the nonempty grids. We conduct experiments on the popular KITTI and NuScenes benchmark, and state-of-the-art performances are achieved in terms of both accuracy and speed.


3D Object Detection Combining Semantic and Geometric Features from Point Clouds

In this paper, we investigate the combination of voxel-based methods and...

PIXOR: Real-time 3D Object Detection from Point Clouds

We address the problem of real-time 3D object detection from point cloud...

RangeRCNN: Towards Fast and Accurate 3D Object Detection with Range Image Representation

We present RangeRCNN, a novel and effective 3D object detection framewor...

PillarNet: Real-Time and High-Performance Pillar-based 3D Object Detection

Real-time and high-performance 3D object detection is of critical import...

ImGeoNet: Image-induced Geometry-aware Voxel Representation for Multi-view 3D Object Detection

We propose ImGeoNet, a multi-view image-based 3D object detection framew...

Redemption from Range-view for Accurate 3D Object Detection

Most recent approaches for 3D object detection predominantly rely on poi...

Sparse Cross-scale Attention Network for Efficient LiDAR Panoptic Segmentation

Two major challenges of 3D LiDAR Panoptic Segmentation (PS) are that poi...

Please sign up or login with your details

Forgot password? Click here to reset