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 551–600 of 1576 papers

TitleStatusHype
Shape Anchor Guided Holistic Indoor Scene UnderstandingCode0
SPOT: Scalable 3D Pre-training via Occupancy Prediction for Learning Transferable 3D Representations—0
MEDL-U: Uncertainty-aware 3D Automatic Annotation based on Evidential Deep LearningCode0
Object2Scene: Putting Objects in Context for Open-Vocabulary 3D Detection—0
Mutual Information-calibrated Conformal Feature Fusion for Uncertainty-Aware Multimodal 3D Object Detection at the Edge—0
Semantics-aware LiDAR-Only Pseudo Point Cloud Generation for 3D Object Detection—0
SupFusion: Supervised LiDAR-Camera Fusion for 3D Object DetectionCode1
Polygon Intersection-over-Union Loss for Viewpoint-Agnostic Monocular 3D Vehicle Detection—0
SCP: Scene Completion Pre-training for 3D Object Detection—0
FusionFormer: A Multi-sensory Fusion in Bird's-Eye-View and Temporal Consistent Transformer for 3D Object Detection—0
Poster: Making Edge-assisted LiDAR Perceptions Robust to Lossy Point Cloud Compression—0
Weakly Supervised Point Clouds Transformer for 3D Object Detection—0
ClusterFusion: Leveraging Radar Spatial Features for Radar-Camera 3D Object Detection in Autonomous Vehicles—0
Diffusion-based 3D Object Detection with Random Boxes—0
Adv3D: Generating 3D Adversarial Examples for 3D Object Detection in Driving Scenarios with NeRF—0
Snow Removal for LiDAR Point Clouds with Spatio-temporal Conditional Random FieldsCode0
S^3-MonoDETR: Supervised Shape&Scale-perceptive Deformable Transformer for Monocular 3D Object DetectionCode0
MS23D: A 3D Object Detection Method Using Multi-Scale Semantic Feature Points to Construct 3D Feature Layer—0
Ego-Motion Estimation and Dynamic Motion Separation from 3D Point Clouds for Accumulating Data and Improving 3D Object Detection—0
3D Adversarial Augmentations for Robust Out-of-Domain Predictions—0
Group Regression for Query Based Object Detection and Tracking—0
SOGDet: Semantic-Occupancy Guided Multi-view 3D Object DetectionCode1
Perspective-aware Convolution for Monocular 3D Object DetectionCode0
On Offline Evaluation of 3D Object Detection for Autonomous Driving—0
I3DOD: Towards Incremental 3D Object Detection via Prompting—0
Advancements in Point Cloud Data Augmentation for Deep Learning: A Survey—0
Delving into Motion-Aware Matching for Monocular 3D Object TrackingCode1
UniM^2AE: Multi-modal Masked Autoencoders with Unified 3D Representation for 3D Perception in Autonomous DrivingCode1
QD-BEV : Quantization-aware View-guided Distillation for Multi-view 3D Object Detection—0
Representation Disparity-aware Distillation for 3D Object Detection—0
ThermRad: A Multi-modal Dataset for Robust 3D Object Detection under Challenging Conditions—0
DatasetEquity: Are All Samples Created Equal? In The Quest For Equity Within DatasetsCode1
SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera VideosCode2
Far3D: Expanding the Horizon for Surround-view 3D Object DetectionCode1
MonoNeRD: NeRF-like Representations for Monocular 3D Object DetectionCode1
ImGeoNet: Image-induced Geometry-aware Voxel Representation for Multi-view 3D Object DetectionCode1
GPA-3D: Geometry-aware Prototype Alignment for Unsupervised Domain Adaptive 3D Object Detection from Point CloudsCode1
UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View RepresentationCode2
PatchContrast: Self-Supervised Pre-training for 3D Object Detection—0
UniWorld: Autonomous Driving Pre-training via World ModelsCode0
PV-SSD: A Multi-Modal Point Cloud Feature Fusion Method for Projection Features and Variable Receptive Field Voxel Features—0
MS3D++: Ensemble of Experts for Multi-Source Unsupervised Domain Adaption in 3D Object DetectionCode1
Reviewing 3D Object Detectors in the Context of High-Resolution 3+1D Radar—0
An Empirical Analysis of Range for 3D Object Detection—0
V-DETR: DETR with Vertex Relative Position Encoding for 3D Object DetectionCode1
FocalFormer3D : Focusing on Hard Instance for 3D Object DetectionCode2
PARTNER: Level up the Polar Representation for LiDAR 3D Object DetectionCode1
FSD V2: Improving Fully Sparse 3D Object Detection with Virtual Voxels—0
QUEST: Query Stream for Practical Cooperative PerceptionCode0
MDT3D: Multi-Dataset Training for LiDAR 3D Object Detection GeneralizationCode0
Show:102550
← PrevPage 12 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