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 351–400 of 1576 papers

TitleStatusHype
CrossDTR: Cross-view and Depth-guided Transformers for 3D Object DetectionCode1
AutoShape: Real-Time Shape-Aware Monocular 3D Object DetectionCode1
DORT: Modeling Dynamic Objects in Recurrent for Multi-Camera 3D Object Detection and TrackingCode1
Deformable PV-RCNN: Improving 3D Object Detection with Learned DeformationsCode1
Delving into Localization Errors for Monocular 3D Object DetectionCode1
Delving into Motion-Aware Matching for Monocular 3D Object TrackingCode1
Ground-aware Monocular 3D Object Detection for Autonomous DrivingCode1
H3DNet: 3D Object Detection Using Hybrid Geometric PrimitivesCode1
HoughNet: Integrating near and long-range evidence for visual detectionCode1
3D Object Detection with a Self-supervised Lidar Scene Flow BackboneCode1
Geometry Uncertainty Projection Network for Monocular 3D Object DetectionCode1
CRN: Camera Radar Net for Accurate, Robust, Efficient 3D PerceptionCode1
GLENet: Boosting 3D Object Detectors with Generative Label Uncertainty EstimationCode1
Density-Insensitive Unsupervised Domain Adaption on 3D Object DetectionCode1
BEV-LGKD: A Unified LiDAR-Guided Knowledge Distillation Framework for BEV 3D Object DetectionCode1
Lite-FPN for Keypoint-based Monocular 3D Object DetectionCode1
A Comprehensive Review of 3D Object Detection in Autonomous Driving: Technological Advances and Future DirectionsCode1
BEV-MAE: Bird's Eye View Masked Autoencoders for Point Cloud Pre-training in Autonomous Driving ScenariosCode1
BEVNeXt: Reviving Dense BEV Frameworks for 3D Object DetectionCode1
Det6D: A Ground-Aware Full-Pose 3D Object Detector for Improving Terrain RobustnessCode1
Geometry-based Distance Decomposition for Monocular 3D Object DetectionCode1
GndNet: Fast Ground Plane Estimation and Point Cloud Segmentation for Autonomous VehiclesCode1
AutoAlignV2: Deformable Feature Aggregation for Dynamic Multi-Modal 3D Object DetectionCode1
CR3DT: Camera-RADAR Fusion for 3D Detection and TrackingCode1
General Geometry-aware Weakly Supervised 3D Object DetectionCode1
DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D QueriesCode1
GeoBEV: Learning Geometric BEV Representation for Multi-view 3D Object DetectionCode1
GO-N3RDet: Geometry Optimized NeRF-enhanced 3D Object DetectorCode1
Fusing Event-based and RGB camera for Robust Object Detection in Adverse ConditionsCode1
Fusion is Not Enough: Single Modal Attacks on Fusion Models for 3D Object DetectionCode1
Fully Sparse Fusion for 3D Object DetectionCode1
CoreNet: Conflict Resolution Network for Point-Pixel Misalignment and Sub-Task Suppression of 3D LiDAR-Camera Object DetectionCode1
FusionPainting: Multimodal Fusion with Adaptive Attention for 3D Object DetectionCode1
Beyond One Shot, Beyond One Perspective: Cross-View and Long-Horizon Distillation for Better LiDAR RepresentationsCode1
CORE: Cooperative Reconstruction for Multi-Agent PerceptionCode1
3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object DetectionCode1
Frustum-PointPillars: A Multi-Stage Approach for 3D Object Detection using RGB Camera and LiDARCode1
Diffusion-SS3D: Diffusion Model for Semi-supervised 3D Object DetectionCode1
FSD-BEV: Foreground Self-Distillation for Multi-view 3D Object DetectionCode1
MonoDistill: Learning Spatial Features for Monocular 3D Object DetectionCode1
BirdNet: a 3D Object Detection Framework from LiDAR informationCode1
MonoLoco: Monocular 3D Pedestrian Localization and Uncertainty EstimationCode1
BirdNet+: End-to-End 3D Object Detection in LiDAR Bird's Eye ViewCode1
MonoNeRD: NeRF-like Representations for Monocular 3D Object DetectionCode1
FrustumFormer: Adaptive Instance-aware Resampling for Multi-view 3D DetectionCode1
MonoSKD: General Distillation Framework for Monocular 3D Object Detection via Spearman Correlation CoefficientCode1
Boosting 3D Object Detection via Object-Focused Image FusionCode1
Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity EstimationCode1
3D Object Detection for Autonomous Driving: A SurveyCode1
Frustum PointNets for 3D Object Detection from RGB-D DataCode1
Show:102550
← PrevPage 8 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
2MegFusionNDS0.77—Unverified
3MMFusion-eNDS0.77—Unverified
4BEVFusion-eNDS0.76—Unverified
5RacoonPowerNDS0.76—Unverified
6DeepInteraction-largeNDS0.76—Unverified
7DeepInteraction-eNDS0.76—Unverified
8FusionVPENDS0.75—Unverified
9FocalFormer3D-FNDS0.75—Unverified
10CenterPoint-FusionNDS0.75—Unverified