SOTAVerified

3D Object Detection

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 )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 901–950 of 1576 papers

TitleStatusHype
Sample, Crop, Track: Self-Supervised Mobile 3D Object Detection for Urban Driving LiDAR—0
Self-supervised 3D Object Detection from Monocular Pseudo-LiDAR—0
Rethinking Dimensionality Reduction in Grid-based 3D Object Detection—0
LidarMultiNet: Towards a Unified Multi-Task Network for LiDAR Perception—0
A Dual-Cycled Cross-View Transformer Network for Unified Road Layout Estimation and 3D Object Detection in the Bird's-Eye-ViewCode1
FFPA-Net: Efficient Feature Fusion with Projection Awareness for 3D Object Detection—0
Viewer-Centred Surface Completion for Unsupervised Domain Adaptation in 3D Object DetectionCode1
CRAFT: Camera-Radar 3D Object Detection with Spatio-Contextual Fusion Transformer—0
CMR3D: Contextualized Multi-Stage Refinement for 3D Object Detection—0
CenterFormer: Center-based Transformer for 3D Object DetectionCode2
Multi-modal Streaming 3D Object Detection—0
MSMDFusion: Fusing LiDAR and Camera at Multiple Scales with Multi-Depth Seeds for 3D Object DetectionCode0
SEFormer: Structure Embedding Transformer for 3D Object Detection—0
Scatter Points in Space: 3D Detection from Multi-view Monocular Images—0
3DLG-Detector: 3D Object Detection via Simultaneous Local-Global Feature Learning—0
PV-RCNN++: Semantical Point-Voxel Feature Interaction for 3D Object Detection—0
Bridging the View Disparity Between Radar and Camera Features for Multi-modal Fusion 3D Object Detection—0
Anytime-Lidar: Deadline-aware 3D Object Detection—0
AGO-Net: Association-Guided 3D Point Cloud Object Detection Network—0
DeepInteraction: 3D Object Detection via Modality InteractionCode2
Quality Matters: Embracing Quality Clues for Robust 3D Multi-Object Tracking—0
Minkowski Tracker: A Sparse Spatio-Temporal R-CNN for Joint Object Detection and Tracking—0
STS: Surround-view Temporal Stereo for Multi-view 3D Detection—0
A Simple Baseline for Multi-Camera 3D Object DetectionCode1
MonoSIM: Simulating Learning Behaviors of Heterogeneous Point Cloud Object Detectors for Monocular 3D Object DetectionCode0
GraVoS: Voxel Selection for 3D Point-Cloud DetectionCode0
Ret3D: Rethinking Object Relations for Efficient 3D Object Detection in Driving Scenes—0
An Empirical Study of Pseudo-Labeling for Image-based 3D Object Detection—0
Aerial Monocular 3D Object DetectionCode0
Graph R-CNN: Towards Accurate 3D Object Detection with Semantic-Decorated Local GraphCode1
Global Hierarchical Attention for 3D Point Cloud Analysis—0
TransPillars: Coarse-to-Fine Aggregation for Multi-Frame 3D Object Detection—0
Ithaca365: Dataset and Driving Perception under Repeated and Challenging Weather Conditions—0
PolarMix: A General Data Augmentation Technique for LiDAR Point CloudsCode2
Semi-supervised 3D Object Detection with Proficient TeachersCode1
Monocular 3D Object Detection with Depth from MotionCode2
ProposalContrast: Unsupervised Pre-training for LiDAR-based 3D Object DetectionCode1
Graph Neural Network and Spatiotemporal Transformer Attention for 3D Video Object Detection from Point Clouds—0
Label-Guided Auxiliary Training Improves 3D Object DetectorCode0
Computer Vision Aided mmWave Beam Alignment in V2X CommunicationsCode0
Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise BinarizationCode1
DBQ-SSD: Dynamic Ball Query for Efficient 3D Object DetectionCode1
DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object DetectionCode2
AutoAlignV2: Deformable Feature Aggregation for Dynamic Multi-Modal 3D Object DetectionCode1
Omni3D: A Large Benchmark and Model for 3D Object Detection in the WildCode2
Boosting 3D Object Detection via Object-Focused Image FusionCode1
Densely Constrained Depth Estimator for Monocular 3D Object DetectionCode1
Multimodal Transformer for Automatic 3D Annotation and Object DetectionCode1
A Novel Neural Network Training Method for Autonomous Driving Using Semi-Pseudo-Labels and 3D Data Augmentations—0
On the Robustness of 3D Object Detectors—0
Show:102550
← PrevPage 19 of 32Next →
All datasetsnuScenesScanNetV2SUN-RGBD valKITTI Cars EasyKITTI Cars HardnuScenes Camera OnlyKITTI Cars Easy valKITTI Cars Moderate valnuscenes Camera-RadarView-of-Delft (val)KITTI Cars Hard valDAIR-V2X-I

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1EA-LSSNDS0.78—Unverified
2MMFusion-eNDS0.77—Unverified
3MegFusionNDS0.77—Unverified
4RacoonPowerNDS0.76—Unverified
5BEVFusion-eNDS0.76—Unverified
6DeepInteraction-largeNDS0.76—Unverified
7DeepInteraction-eNDS0.76—Unverified
8DAANDS0.75—Unverified
9FusionVPENDS0.75—Unverified
10CenterPoint-FusionNDS0.75—Unverified