3D Object Detection

585 papers with code • 55 benchmarks • 48 datasets

3D Object Detection is a task in computer vision where the goal is to identify and locate objects in a 3D environment based on their shape, location, and orientation. It involves detecting the presence of objects and determining their location in the 3D space in real-time. This task is crucial for applications such as autonomous vehicles, robotics, and augmented reality.

( Image credit: AVOD )

Benchmarks

Add a Result

These leaderboards are used to track progress in 3D Object Detection

Dataset	Best Model	Compare
KITTI Cars Moderate	GLENet-VR	See all
nuScenes	EA-LSS	See all
SUN-RGBD val	Point-GCC+TR3D+FF	See all
ScanNetV2	UDeerLvic	See all
KITTI Cars Easy	GLENet-VR	See all
KITTI Cars Hard	3D Dual-Fusion	See all
nuScenes Camera Only	Far3D	See all
KITTI Pedestrians Moderate	3D-FCT	See all
KITTI Cyclists Easy	3D-FCT	See all
KITTI Cyclists Moderate	3D-FCT	See all
KITTI Cyclists Hard	SA-Det3D	See all
KITTI Cars Easy val	SA-SSD+EBM	See all
KITTI Cars Moderate val	SA-SSD+EBM	See all
KITTI Cars Hard val	M3DeTR	See all
KITTI Pedestrians Easy	IPOD	See all
KITTI Pedestrians Hard	SVGA-Net	See all
DAIR-V2X-I	MonoUNI	See all
nuscenes Camera-Radar	HyDRa	See all
waymo vehicle	PillarNeXt	See all
Rope3D	MonoUNI	See all
SUN-RGBD	CAGroup3D (Geo Only)	See all
waymo cyclist	DSVT(val)	See all
waymo pedestrian	DSVT(val)	See all
S3DIS	Point-GCC+TR3D	See all
V2XSet	V2X-ViT	See all
nuScenes LiDAR only	DSVT	See all
OPV2V	V2VNet (PointPillar backbone)	See all
KITTI Pedestrian Easy val	PVCNN	See all
KITTI Pedestrian Moderate val	PVCNN	See all
KITTI Pedestrian Hard val	PVCNN	See all
KITTI Cyclist Easy val	PVCNN	See all
KITTI Cyclist Moderate val	PVCNN	See all
KITTI Cyclist Hard val	F-PointNet++ [Qi:2018fd]	See all
aiMotive Dataset	Lidar-Radar-Camera	See all
3D Object Detection on Argoverse2 Camera Only	Far3D	See all
waymo all_ns	CenterPoint	See all
NYU Depth v2	SGPN-CNN	See all
nuScenes-F	RRPN + R101 - F	See all
nuScenes-FB	RRPN + R101 - FB	See all
KITTI Pedestrian Hard	PiFeNet	See all
KITTI Cyclists Moderate val	Deformable PV-RCNN	See all
KITTI Pedestrians Moderate val	Deformable PV-RCNN	See all
Dense Fog	PV-RCNN	See all
KITTI Pedestrian Moderate	PiFeNet	See all
Heavy Snowfall	PV-RCNN	See all
Light Snowfall	PV-RCNN	See all
Clear Weather	PV-RCNN	See all
KITTI Pedestrian Easy	PiFeNet	See all
KITTI Pedestrian	PiFeNet	See all
V2X-SIM	Where2comm	See all
DAIR-V2X	CoBEVFlow	See all
Argoverse2	VoxelNeXt	See all
Cityscapes 3D	TaskPrompter	See all
Argoverse	ky_nctu_mo	See all
IRV2V	CoBEVFlow	See all

Show all 55 benchmarks

Collapse benchmarks

Libraries

Use these libraries to find 3D Object Detection models and implementations

open-mmlab/mmdetection3d

14 papers

4,810

PaddlePaddle/Paddle3D

6 papers

537

open-mmlab/OpenPCDet

5 papers

4,323

DerrickXuNu/OpenCOOD

5 papers

594

See all 11 libraries.

Datasets

Subtasks

Robust 3D Object Detection

Robust BEV Detection

Most implemented papers

Most implemented Social Latest No code

PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation

mialbro/PointFusion • • CVPR 2018

We present PointFusion, a generic 3D object detection method that leverages both image and 3D point cloud information.

Paper
Code

PointSeg: Real-Time Semantic Segmentation Based on 3D LiDAR Point Cloud

ywangeq/PointSeg • • 17 Jul 2018

We take the spherical image, which is transformed from the 3D LiDAR point clouds, as input of the convolutional neural networks (CNNs) to predict the point-wise semantic map.

Paper
Code

MonoLoco: Monocular 3D Pedestrian Localization and Uncertainty Estimation

vita-epfl/monoloco • • ICCV 2019

We tackle the fundamentally ill-posed problem of 3D human localization from monocular RGB images.

Paper
Code

Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection

poodarchu/Class-balanced-Grouping-and-Sampling-for-Point-Cloud-3D-Object-Detection • • 26 Aug 2019

This report presents our method which wins the nuScenes3D Detection Challenge [17] held in Workshop on Autonomous Driving(WAD, CVPR 2019).

Paper
Code

Deep Learning for 3D Point Clouds: A Survey

QingyongHu/SoTA-Point-Cloud • 27 Dec 2019

To stimulate future research, this paper presents a comprehensive review of recent progress in deep learning methods for point clouds.

Paper
Code

SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation

lzccccc/SMOKE • • 24 Feb 2020

Estimating 3D orientation and translation of objects is essential for infrastructure-less autonomous navigation and driving.

Paper
Code

V2VNet: Vehicle-to-Vehicle Communication for Joint Perception and Prediction

DerrickXuNu/OpenCOOD • • ECCV 2020

In this paper, we explore the use of vehicle-to-vehicle (V2V) communication to improve the perception and motion forecasting performance of self-driving vehicles.

Paper
Code

CenterFusion: Center-based Radar and Camera Fusion for 3D Object Detection

mrnabati/CenterFusion • • 10 Nov 2020

In this paper, we focus on the problem of radar and camera sensor fusion and propose a middle-fusion approach to exploit both radar and camera data for 3D object detection.

Paper
Code