3D Object Detection

Edit

26 papers with code · Computer Vision

Subtask of Object Detection

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

State-of-the-art leaderboards

Add a result

Dataset	Best Method	Paper title	Compare
KITTI Cars Moderate	UberATG-MMF	Multi-Task Multi-Sensor Fusion for 3D Object Detection	See all
KITTI Cars Hard	UberATG-MMF	Multi-Task Multi-Sensor Fusion for 3D Object Detection	See all
KITTI Cars Easy	UberATG-MMF	Multi-Task Multi-Sensor Fusion for 3D Object Detection	See all
KITTI Cyclists Hard	F-ConvNets	Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detection	See all
KITTI Cyclists Moderate	F-ConvNet	Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 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 Pedestrians Moderate	F-ConvNet	Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detection	See all
KITTI Pedestrians Hard	IPOD	IPOD: Intensive Point-based Object Detector for Point Cloud	See all
KITTI Pedestrians Easy	IPOD	IPOD: Intensive Point-based Object Detector for Point Cloud	See all
SUN-RGBD	Frustum PointNets	Frustum PointNets for 3D Object Detection from RGB-D Data	See all
NYU Depth v2	SGPN-CNN	SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation	See all

Greatest papers with code

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

CVPR 2018 • charlesq34/pointnet •

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

SOTA for 3D Object Detection on KITTI Pedestrians Moderate

3D OBJECT DETECTION OBJECT LOCALIZATION

2,026

Paper
Code

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

CVPR 2018 • charlesq34/pointnet •

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.

SOTA for Object Localization on KITTI Cars Easy

3D OBJECT DETECTION AUTONOMOUS NAVIGATION FEATURE ENGINEERING OBJECT LOCALIZATION

2,026

Paper
Code

Joint 3D Proposal Generation and Object Detection from View Aggregation

6 Dec 2017 • kujason/avod •

We present AVOD, an Aggregate View Object Detection network for autonomous driving scenarios.

#2 best model for 3D Object Detection on KITTI Cars Hard

3D OBJECT DETECTION AUTONOMOUS DRIVING

510

Paper
Code

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

CVPR 2019 • sshaoshuai/PointRCNN •

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

SOTA for 3D Object Detection on KITTI Cars Hard

3D OBJECT DETECTION OBJECT PROPOSAL GENERATION

466

Paper
Code

SBNet: Sparse Blocks Network for Fast Inference

CVPR 2018 • uber/sbnet •

Conventional deep convolutional neural networks (CNNs) apply convolution operators uniformly in space across all feature maps for hundreds of layers - this incurs a high computational cost for real-time applications.

3D OBJECT DETECTION OBJECT CLASSIFICATION SEMANTIC SEGMENTATION

368

Paper
Code