SOTAVerified

Autonomous Driving

Autonomous driving is the task of driving a vehicle without human conduction.

Many of the state-of-the-art results can be found at more general task pages such as 3D Object Detection and Semantic Segmentation.

(Image credit: Exploring the Limitations of Behavior Cloning for Autonomous Driving)

Papers

Showing 651675 of 6092 papers

TitleStatusHype
High-level camera-LiDAR fusion for 3D object detection with machine learningCode1
HFT: Lifting Perspective Representations via Hybrid Feature TransformationCode1
A Comprehensive Review of 3D Object Detection in Autonomous Driving: Technological Advances and Future DirectionsCode1
A Good Foundation is Worth Many Labels: Label-Efficient Panoptic SegmentationCode1
DASGIL: Domain Adaptation for Semantic and Geometric-aware Image-based LocalizationCode1
HiLoTs: High-Low Temporal Sensitive Representation Learning for Semi-Supervised LiDAR Segmentation in Autonomous DrivingCode1
Curricular Subgoals for Inverse Reinforcement LearningCode1
Ctrl-V: Higher Fidelity Video Generation with Bounding-Box Controlled Object MotionCode1
HEDNet: A Hierarchical Encoder-Decoder Network for 3D Object Detection in Point CloudsCode1
Agent-X: Evaluating Deep Multimodal Reasoning in Vision-Centric Agentic TasksCode1
CSFlow: Learning Optical Flow via Cross Strip Correlation for Autonomous DrivingCode1
CurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point BlendingCode1
Cross-modal Learning for Domain Adaptation in 3D Semantic SegmentationCode1
HEAL-SWIN: A Vision Transformer On The SphereCode1
CrossDTR: Cross-view and Depth-guided Transformers for 3D Object DetectionCode1
MambaST: A Plug-and-Play Cross-Spectral Spatial-Temporal Fuser for Efficient Pedestrian DetectionCode1
A Unified Probabilistic Approach to Traffic Conflict DetectionCode1
CROON: Automatic Multi-LiDAR Calibration and Refinement Method in Road SceneCode1
Crowdsourced 3D Mapping: A Combined Multi-View Geometry and Self-Supervised Learning ApproachCode1
Heatmap-based Object Detection and Tracking with a Fully Convolutional Neural NetworkCode1
Hindsight is 20/20: Leveraging Past Traversals to Aid 3D PerceptionCode1
A Unified Query-based Paradigm for Point Cloud UnderstandingCode1
CPGNet: Cascade Point-Grid Fusion Network for Real-Time LiDAR Semantic SegmentationCode1
AutoAlignV2: Deformable Feature Aggregation for Dynamic Multi-Modal 3D Object DetectionCode1
CR3DT: Camera-RADAR Fusion for 3D Detection and TrackingCode1
Show:102550
← PrevPage 27 of 244Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ReasonNetDriving Score79.95Unverified
2InterFuserDriving Score76.18Unverified
3TCPDriving Score75.14Unverified
4TF++ WPDriving Score66.32Unverified
5Learning From All Vehicles (LAV)Driving Score61.85Unverified
6TransFuserDriving Score61.18Unverified
7TransFuser (Reproduced)Driving Score55.04Unverified
8TCP (Reproduced)Driving Score47.91Unverified
9Latent TransFuserDriving Score45.2Unverified
10GRIADDriving Score36.79Unverified
#ModelMetricClaimedVerifiedStatus
1Geometric FusionRC69.17Unverified
2TransFuserRC56.36Unverified
#ModelMetricClaimedVerifiedStatus
1Geometric FusionRC86.91Unverified
2TransFuserRC78.41Unverified