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 301–350 of 1576 papers

TitleStatusHype
Faraway-Frustum: Dealing with Lidar Sparsity for 3D Object Detection using FusionCode1
FASTer: Focal Token Acquiring-and-Scaling Transformer for Long-term 3D Object DetectionCode1
DatasetEquity: Are All Samples Created Equal? In The Quest For Equity Within DatasetsCode1
Behind the Curtain: Learning Occluded Shapes for 3D Object DetectionCode1
MASS: Multi-Attentional Semantic Segmentation of LiDAR Data for Dense Top-View UnderstandingCode1
D-Align: Dual Query Co-attention Network for 3D Object Detection Based on Multi-frame Point Cloud SequenceCode1
Exploring Active 3D Object Detection from a Generalization PerspectiveCode1
Fully Sparse Fusion for 3D Object DetectionCode1
Back-tracing Representative Points for Voting-based 3D Object Detection in Point CloudsCode1
Ev-3DOD: Pushing the Temporal Boundaries of 3D Object Detection with Event CamerasCode1
Evaluating Adversarial Attacks on Driving Safety in Vision-Based Autonomous VehiclesCode1
Masked Autoencoder for Self-Supervised Pre-training on Lidar Point CloudsCode1
MetaBEV: Solving Sensor Failures for BEV Detection and Map SegmentationCode1
Mono3DVG: 3D Visual Grounding in Monocular ImagesCode1
Back to Reality: Weakly-supervised 3D Object Detection with Shape-guided Label EnhancementCode1
Curricular Object Manipulation in LiDAR-based Object DetectionCode1
Constructing Metric-Semantic Maps using Floor Plan Priors for Long-Term Indoor LocalizationCode1
Enhancing 3D Object Detection with 2D Detection-Guided Query AnchorsCode1
Lite-FPN for Keypoint-based Monocular 3D Object DetectionCode1
LSSInst: Improving Geometric Modeling in LSS-Based BEV Perception with Instance RepresentationCode1
AYDIV: Adaptable Yielding 3D Object Detection via Integrated Contextual Vision TransformerCode1
ES6D: A Computation Efficient and Symmetry-Aware 6D Pose Regression FrameworkCode1
CubeSLAM: Monocular 3D Object SLAMCode1
FastPillars: A Deployment-friendly Pillar-based 3D DetectorCode1
End-To-End Optimization of LiDAR Beam Configuration for 3D Object Detection and LocalizationCode1
End-to-End Pseudo-LiDAR for Image-Based 3D Object DetectionCode1
LiRaFusion: Deep Adaptive LiDAR-Radar Fusion for 3D Object DetectionCode1
M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with TransformersCode1
DBQ-SSD: Dynamic Ball Query for Efficient 3D Object DetectionCode1
DCDet: Dynamic Cross-based 3D Object DetectorCode1
CRT-Fusion: Camera, Radar, Temporal Fusion Using Motion Information for 3D Object DetectionCode1
Benchmarking Robustness of 3D Object Detection to Common CorruptionsCode1
Benchmarking the Robustness of LiDAR-Camera Fusion for 3D Object DetectionCode1
FADet: A Multi-sensor 3D Object Detection Network based on Local Featured AttentionCode1
3D Object Detection from Images for Autonomous Driving: A SurveyCode1
AD-L-JEPA: Self-Supervised Spatial World Models with Joint Embedding Predictive Architecture for Autonomous Driving with LiDAR DataCode1
Cross-Modality Knowledge Distillation Network for Monocular 3D Object DetectionCode1
Lightweight LiDAR-Camera 3D Dynamic Object Detection and Multi-Class Trajectory PredictionCode1
LinK: Linear Kernel for LiDAR-based 3D PerceptionCode1
Deep Dive Into Gradients: Better Optimization for 3D Object Detection With Gradient-Corrected IoU SupervisionCode1
A Comprehensive Study of the Robustness for LiDAR-based 3D Object Detectors against Adversarial AttacksCode1
EPNet++: Cascade Bi-directional Fusion for Multi-Modal 3D Object DetectionCode1
Deep Hough Voting for 3D Object Detection in Point CloudsCode1
CrossDTR: Cross-view and Depth-guided Transformers for 3D Object DetectionCode1
AutoShape: Real-Time Shape-Aware Monocular 3D Object DetectionCode1
Finding Your (3D) Center: 3D Object Detection Using a Learned LossCode1
M3D-RPN: Monocular 3D Region Proposal Network for Object DetectionCode1
DynOPETs: A Versatile Benchmark for Dynamic Object Pose Estimation and Tracking in Moving Camera ScenariosCode1
CRN: Camera Radar Net for Accurate, Robust, Efficient 3D PerceptionCode1
EarlyBird: Early-Fusion for Multi-View Tracking in the Bird's Eye ViewCode1
Show:102550
← PrevPage 7 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