Joint 3D Proposal Generation and Object Detection from View Aggregation

Jason Ku, Melissa Mozifian, Jungwook Lee, Ali Harakeh, Steven Waslander
12/6/2017
cs.CV

Official code: kujason/avod (959 stars, MIT, last commit 2026-02-05).

Abstract

We present AVOD, an Aggregate View Object Detection network for autonomous driving scenarios. The proposed neural network architecture uses LIDAR point clouds and RGB images to generate features that are shared by two subnetworks: a region proposal network (RPN) and a second stage detector network. The proposed RPN uses a novel architecture capable of performing multimodal feature fusion on high resolution feature maps to generate reliable 3D object proposals for multiple object classes in road scenes. Using these proposals, the second stage detection network performs accurate oriented 3D bounding box regression and category classification to predict the extents, orientation, and classification of objects in 3D space. Our proposed architecture is shown to produce state of the art results on the KITTI 3D object detection benchmark while running in real time with a low memory footprint, making it a suitable candidate for deployment on autonomous vehicles. Code is at: https://github.com/kujason/avod

View on arXivView PDF

Code Implementations(1)

kujason/avodOfficial100%
MIT

Code for 3D object detection for autonomous driving

959347C++, ShellFeb 28, 20188 months agoMIT
deep-learningobject-detection

Similar Papers

Automatic Vehicle Detection using DETR: A Transformer-Based Approach for Navigating Treacherous Roads

84% match2025

GraphRelate3D: Context-Dependent 3D Object Detection with Inter-Object Relationship Graphs

84% match2024

Implementation of a perception system for autonomous vehicles using a detection-segmentation network in SoC FPGA

84% match1 repo172023

Detection-segmentation convolutional neural network for autonomous vehicle perception

84% match1 repo282023

InfraParis: A multi-modal and multi-task autonomous driving dataset

84% match1 repo62023

SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real-Time Object Detection for Autonomous Driving

84% match1 repo7412016

Cite this paper

@article{ku2017joint,
  title  = {Joint 3D Proposal Generation and Object Detection from View Aggregation},
  author = {Jason Ku and Melissa Mozifian and Jungwook Lee and Ali Harakeh and Steven Waslander},
  year   = {2017},
  eprint = {1712.02294},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1712.02294}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1712.02294.svg)](https://codeofpaper.com/paper/1712.02294)

Discussion