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 201–225 of 1576 papers

TitleStatusHype
Fine-Grained Pillar Feature Encoding Via Spatio-Temporal Virtual Grid for 3D Object DetectionCode1
3DPPE: 3D Point Positional Encoding for Multi-Camera 3D Object Detection TransformersCode1
Aligning Bird-Eye View Representation of Point Cloud Sequences using Scene FlowCode1
Bootstraping Clustering of Gaussians for View-consistent 3D Scene UnderstandingCode1
DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D QueriesCode1
Among Us: Adversarially Robust Collaborative Perception by ConsensusCode1
Bounding Box Disparity: 3D Metrics for Object Detection With Full Degree of FreedomCode1
A Multimodal Hybrid Late-Cascade Fusion Network for Enhanced 3D Object DetectionCode1
Flow-Based Feature Fusion for Vehicle-Infrastructure Cooperative 3D Object DetectionCode1
BoxeR: Box-Attention for 2D and 3D TransformersCode1
Boosting 3D Object Detection via Object-Focused Image FusionCode1
DiffuBox: Refining 3D Object Detection with Point DiffusionCode1
Det6D: A Ground-Aware Full-Pose 3D Object Detector for Improving Terrain RobustnessCode1
Bridging the Domain Gap for Multi-Agent PerceptionCode1
Bridging the Domain Gap: Self-Supervised 3D Scene Understanding with Foundation ModelsCode1
3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance SegmentationCode1
BSH-Det3D: Improving 3D Object Detection with BEV Shape HeatmapCode1
An End-to-End Transformer Model for 3D Object DetectionCode1
BirdNet+: End-to-End 3D Object Detection in LiDAR Bird's Eye ViewCode1
BirdNet: a 3D Object Detection Framework from LiDAR informationCode1
CaKDP: Category-aware Knowledge Distillation and Pruning Framework for Lightweight 3D Object DetectionCode1
Calibration-free BEV Representation for Infrastructure PerceptionCode1
DID-M3D: Decoupling Instance Depth for Monocular 3D Object DetectionCode1
Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise BinarizationCode1
Density-Insensitive Unsupervised Domain Adaption on 3D Object DetectionCode1
Show:102550
← PrevPage 9 of 64Next →
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