自动驾驶感知、端到端论文集（2024-10-11）

1. Detection

• LabelDistill: Label-guided Cross-modal Knowledge Distillation for Camera-based 3D Object Detection ECCV 2024 (已开源)；Paper
• Semi-Supervised Domain Adaptation Using Target-Oriented Domain Augmentation for 3D Object Detection T-IV 2024 (已开源)； Paper
• LiRaFusion: Deep Adaptive LiDAR-Radar Fusion for 3D Object Detection ICRA 2024 （已开源）; Paper;Code
• CRKD: Enhanced Camera-Radar Object Detection with Cross-modality Knowledge Distillation CVPR 2024 (已开源); Project
• RadarDistill: Boosting Radar-based Object Detection Performance via Knowledge Distillation from LiDAR Features CVPR 2024 ;Paper;
• RCBEVDet: Radar-camera Fusion in Bird’s Eye View for 3D Object Detection CVPR 2024 (已开源) ;Paper;Code
• CRN: Camera Radar Net for Accurate, Robust, Efficient 3D Perception ICCV 2023（已开源）;Paper;Code
• FUTR3D: A Unified Sensor Fusion Framework for 3D Detection CVPRW 2023 （已开源） ;Project
• BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird’s-Eye View Representation ICRA 2023（已开源）; Project
• Radar Enlighten the Dark: Enhancing Low-Visibility Perception for Automated Vehicles with Camera-Radar Fusion ITSC 2023（已开源）; Paper; Code
• Unleashing HyDRa: Hybrid Fusion, Depth Consistency and Radar for Unified 3D Perception; Paper; Code

2. Segmentation（Map）

• BEVCar: Camera-Radar Fusion for BEV Map and Object Segmentation IROS 2024 （已开源） ; Project
• Mask2Map: Vectorized HD Map Construction Using Bird’s Eye View Segmentation Masks ECCV2024 (已开源)；Paper
• Simple-BEV: What Really Matters for Multi-Sensor BEV Perception? ICRA 2023 （已开源） ;Project

3. Depth Estimation

• RadarCam-Depth: Radar-Camera Fusion for Depth Estimation with Learned Metric Scale ICRA 2024 （已开源） ; Paper;Code

4. High Resolution

• Towards Dense and Accurate Radar Perception Via Efficient Cross-Modal Diffusion Model RA-L 2024 (已开源)；Paper;Code
• High Resolution Point Clouds from mmWave Radar ICRA 2023 （已开源）;Paper;Code

5. End-to-End Autonomous Driving

• Does end-to-end Autonomus Driving Really Need Perception Tasks?; Paper
• HE-DRIVE: Human-Like end-to-end Driving With Vision Language Models (已开源); Project
• ParkingE2E: Camera-based End-to-end Parking Network, from Images to Planning IROS 2024 (已开源); Paper
• SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representation (已开源); Paper
• GenAD: Generative End-to-End Autonomous Driving ECCV2024 (已开源); Paper