3D Object Detection

Edit

155 papers with code • 32 benchmarks • 16 datasets

2D object detection classifies the object category and estimates oriented 2D bounding boxes of physical objects from 3D sensor data.

( Image credit: AVOD )

Benchmarks

Add a Result

Dataset	Best Model	Paper Title	Compare
KITTI Cars Moderate	SE-SSD	SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloud	See all
KITTI Cars Easy	SVGA-Net	SVGA-Net: Sparse Voxel-Graph Attention Network for 3D Object Detection from Point Clouds	See all
KITTI Cars Hard	PV-RCNN++	PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection	See all
KITTI Cyclists Easy	F-ConvNet	Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detection	See all
KITTI Cyclists Moderate	SVGA-Net	SVGA-Net: Sparse Voxel-Graph Attention Network for 3D Object Detection from Point Clouds	See all
KITTI Cyclists Hard	PV-RCNN	PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection	See all
ScanNetV2	GroupFree3D	Group-Free 3D Object Detection via Transformers	See all
nuScenes	CenterPoint-Fusion		See all
KITTI Pedestrians Moderate	SVGA-Net	SVGA-Net: Sparse Voxel-Graph Attention Network for 3D Object Detection from Point Clouds	See all
SUN-RGBD val	GroupFree3D(Geo only)	Group-Free 3D Object Detection via Transformers	See all
KITTI Cars Easy val	SA-SSD+EBM	Accurate 3D Object Detection using Energy-Based Models	See all
KITTI Cars Moderate val	SA-SSD+EBM	Accurate 3D Object Detection using Energy-Based Models	See all
KITTI Cars Hard val	PV-RCNN++	PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection	See all
KITTI Pedestrians Easy	IPOD	IPOD: Intensive Point-based Object Detector for Point Cloud	See all
KITTI Pedestrians Hard	SVGA-Net	SVGA-Net: Sparse Voxel-Graph Attention Network for 3D Object Detection from Point Clouds	See all
SUN-RGBD	ImVoteNet	ImVoteNet: Boosting 3D Object Detection in Point Clouds with Image Votes	See all
KITTI Pedestrian Easy val	PVCNN	Point-Voxel CNN for Efficient 3D Deep Learning	See all
KITTI Pedestrian Moderate val	PVCNN	Point-Voxel CNN for Efficient 3D Deep Learning	See all
KITTI Pedestrian Hard val	PVCNN	Point-Voxel CNN for Efficient 3D Deep Learning	See all
KITTI Cyclist Easy val	PVCNN	Point-Voxel CNN for Efficient 3D Deep Learning	See all
KITTI Cyclist Moderate val	PVCNN	Point-Voxel CNN for Efficient 3D Deep Learning	See all
KITTI Cyclist Hard val	PVCNN	Point-Voxel CNN for Efficient 3D Deep Learning	See all
waymo all_ns	CenterPoint	Center-based 3D Object Detection and Tracking	See all
waymo cyclist	CenterPoint	Center-based 3D Object Detection and Tracking	See all
waymo pedestrian	CenterPoint	Center-based 3D Object Detection and Tracking	See all
NYU Depth v2	SGPN-CNN	SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation	See all
nuScenes-F	RRPN + R101 - F	RRPN: Radar Region Proposal Network for Object Detection in Autonomous Vehicles	See all
nuScenes-FB	RRPN + R101 - FB	RRPN: Radar Region Proposal Network for Object Detection in Autonomous Vehicles	See all
waymo vehicle	PV-RCNN	PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection	See all
KITTI Cyclists Moderate val	Deformable PV-RCNN	Deformable PV-RCNN: Improving 3D Object Detection with Learned Deformations	See all
KITTI Pedestrians Moderate val	Deformable PV-RCNN	Deformable PV-RCNN: Improving 3D Object Detection with Learned Deformations	See all
Argoverse	ky_nctu_mo		See all

Show all 32 benchmarks

Collapse benchmarks

Datasets

Subtasks

Monocular 3D Object Detection

Greatest papers with code

Frustum PointNets for 3D Object Detection from RGB-D Data

charlesq34/pointnet • • CVPR 2018

In this work, we study 3D object detection from RGB-D data in both indoor and outdoor scenes.

Ranked #1 on Object Localization on KITTI Cyclists Moderate

3D Object Detection Object Localization +1

3,323

Paper
Code

VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection

charlesq34/pointnet • • CVPR 2018

Accurate detection of objects in 3D point clouds is a central problem in many applications, such as autonomous navigation, housekeeping robots, and augmented/virtual reality.

Ranked #1 on Object Localization on KITTI Cars Easy

3D Object Detection Autonomous Navigation +4

3,323

Paper
Code

PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection

open-mmlab/OpenPCDet • • 31 Jan 2021

Second, we propose a more advanced framework, PV-RCNN-v2, for more efficient and accurate 3D detection.

Ranked #1 on 3D Object Detection on KITTI Cars Hard val

3D Object Detection

1,847

Paper
Code

PV-RCNN: The Top-Performing LiDAR-only Solutions for 3D Detection / 3D Tracking / Domain Adaptation of Waymo Open Dataset Challenges

open-mmlab/OpenPCDet • • 28 Aug 2020

In this technical report, we present the top-performing LiDAR-only solutions for 3D detection, 3D tracking and domain adaptation three tracks in Waymo Open Dataset Challenges 2020.

3D Object Detection Domain Adaptation

1,847

Paper
Code

PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection

sshaoshuai/PointCloudDet3D • • CVPR 2020

We present a novel and high-performance 3D object detection framework, named PointVoxel-RCNN (PV-RCNN), for accurate 3D object detection from point clouds.

Ranked #1 on Birds Eye View Object Detection on KITTI Cyclists Moderate

3D Object Detection

1,847

Paper
Code

From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network

open-mmlab/OpenPCDet • • 8 Jul 2019

3D object detection from LiDAR point cloud is a challenging problem in 3D scene understanding and has many practical applications.

3D Object Detection Scene Understanding

1,847

Paper
Code

PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud

sshaoshuai/PointCloudDet3D • • CVPR 2019

In this paper, we propose PointRCNN for 3D object detection from raw point cloud.

Ranked #2 on Object Detection on KITTI Cars Hard

3D Object Detection Object Proposal Generation

1,847

Paper
Code

Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotations

google-research-datasets/Objectron • • CVPR 2021

3D object detection has recently become popular due to many applications in robotics, augmented reality, autonomy, and image retrieval.

Ranked #1 on Monocular 3D Object Detection on Google Objectron

3D Object Tracking 3D Shape Representation +3

1,486

Paper
Code

FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection

open-mmlab/mmdetection3d • • 22 Apr 2021

In this technical report, we study this problem with a practice built on fully convolutional single-stage detector and propose a general framework FCOS3D.

Ranked #50 on 3D Object Detection on nuScenes

Autonomous Driving Monocular 3D Object Detection

1,351

Paper
Code

Exploring Data Augmentation for Multi-Modality 3D Object Detection

open-mmlab/mmdetection3d • • 23 Dec 2020

Due to the fact that multi-modality data augmentation must maintain consistency between point cloud and images, recent methods in this field typically use relatively insufficient data augmentation.

3D Object Detection Autonomous Driving +1

1,351

Paper
Code

3D Object Detection Edit

Benchmarks Add a Result

Datasets

Subtasks

Greatest papers with code

3D Object Detection

Edit

Benchmarks

Add a Result