ICRA2024 自动驾驶相关Paper整理

作者 | 牛牛牛肉饭  编辑 | 汽车人

原文链接：https://zhuanlan.zhihu.com/p/697604761

点击下方卡片，关注“自动驾驶之心”公众号

戳我-> 领取自动驾驶近15个方向学习路线

>>点击进入→自动驾驶之心技术交流群

本文只做学术分享，如有侵权，联系删文

3D 目标检测任务

1. Better Monocular 3D Detectors with LiDAR from the Past

2. LET-3D-AP: Longitudinal Error Tolerant 3D Average Precision for Camera-Only 3D Detection

3. BEVUDA: Multi-Geometric Space Alignments for Domain Adaptive BEV 3D Object Detection

4. AYDIV: Adaptable Yielding 3D Object Detection Via Integrated Contextual Vision Transformer

5. Multimodal Object Query Initialization for 3D Object Detection

6. LiDAR-CS Dataset: LiDAR Point Cloud Dataset with Cross-Sensors for 3D Object Detection

7. 2D-3D Object Shape Alignment for Camera-Object Pose Compensation in Object-Visual SLAM

8. ProEqBEV: Product Group Equivariant BEV Network for 3D Object Detection in Road Scenes of Autonomous Driving

9. Eliminating Cross-Modal Conflicts in BEV Space for LiDAR-Camera 3D Object Detection

10. EMIFF: Enhanced Multi-Scale Image Feature Fusion for Vehicle-Infrastructure Cooperative 3D Object Detection

11. WLST: Weak Labels Guided Self-Training for Weakly-Supervised Domain Adaptation on 3D Object Detection

12. Towards a Robust Sensor Fusion Step for 3D Object Detection on Corrupted Data

13. RCM-Fusion: Radar-Camera Multi-Level Fusion for 3D Object Detection

14. LiRaFusion: Deep Adaptive LiDAR-Radar Fusion for 3D Object Detection

15. CenterCoop: Center-Based Feature Aggregation for Communication-Efficient Vehicle-Infrastructure Cooperative 3D Object Detection

16. Talk2BEV: Language-Enhanced Bird's-Eye View Maps for Autonomous Driving

地图构建 Map Construction

1. BroadBEV: Collaborative LiDAR-Camera Fusion for Broad-Sighted Bird's Eye View Map Construction

2. MBFusion: A New Multi-Modal BEV Feature Fusion Method for HD Map Construction

3. RH-Map: Online Map Construction Framework of Dynamic Object Removal Based on 3D Region-Wise Hash Map Structure

4. AutoMerge: A Framework for Map Assembling and Smoothing in City-Scale Environments

5. Complementing Onboard Sensors with Satellite Maps: A New Perspective for HD Map Construction

6. Skeleton Disk-Graph Roadmap: A Sparse Deterministic Roadmap for Safe 2D Navigation and Exploration

语义分割 Semantic Segmentation

1. Semi-Supervised Learning for Visual Bird's Eye View Semantic Segmentation

2. One-Vs-All Semi-Automatic Labeling Tool for Semantic Segmentation in Autonomous Driving

3. Discwise Active Learning for LiDAR Semantic Segmentation

4. Distribution-Aware Continual Test-Time Adaptation for Semantic Segmentation

5. PCB-RandNet: Rethinking Random Sampling for LiDAR Semantic Segmentation in Autonomous Driving Scene

6. Improving Radial Imbalances with Hybrid Voxelization and RadialMix for LiDAR 3D Semantic Segmentation

7. DefFusion: Deformable Multimodal Representation Fusion for 3D Semantic Segmentation

8. CMDFusion: Bidirectional Fusion Network with Cross-Modality Knowledge Distillation for LIDAR Semantic Segmentation

9. Uplifting Range-View-Based 3D Semantic Segmentation in Real-Time with Multi-Sensor Fusion

Occupancy

1. FastOcc: Accelerating 3D Occupancy Prediction by Fusing the 2D Bird's-Eye View and Perspective View

2. RenderOcc: Vision-Centric 3D Occupancy Prediction with 2D Rendering Supervision

3. CVFormer: Learning Circum-View Representation and Consistency Constraints for Vision-Based Occupancy Prediction Via Transformers

4. OCC-VO: Dense Mapping Via 3D Occupancy-Based Visual Odometry for Autonomous Driving

5. MonoOcc: Digging into Monocular Semantic Occupancy Prediction

车道线感知

1. Bi²Lane: Bi-Directional Temporal Refinement with Bi-Level Feature Aggregation for 3D Lane Detection

2. Augmenting Lane Perception and Topology Understanding with Standard Definition Navigation Maps

3. Advancements in 3D Lane Detection Using LiDAR Point Clouds: From Data Collection to Model Development

数据集 Dataset

1. Campus Map: A Large-Scale Dataset to Support Multi-View VO, SLAM and BEV Estimation

2. Towards Learning-Based Planning: The nuPlan Benchmark for Real-World Autonomous Driving

3. CC-SGG: Corner Case Scenario Generation Using Learned Scene Graphs

4. WOMD-LiDAR: Raw Sensor Dataset Benchmark for Motion Forecasting

5. AD4RL: Autonomous Driving Benchmarks for Offline Reinforcement Learning with Value-Based Dataset

6. LiDAR-CS Dataset: LiDAR Point Cloud Dataset with Cross-Sensors for 3D Object Detection

7. CoAS-Net: Context-Aware Suction Network with a Large-Scale Domain Randomized Synthetic Dataset

投稿作者为『自动驾驶之心知识星球』特邀嘉宾，欢迎加入交流！

① 全网独家视频课程

BEV感知、BEV模型部署、BEV目标跟踪、毫米波雷达视觉融合、多传感器标定、多传感器融合、多模态3D目标检测、车道线检测、轨迹预测、在线高精地图、世界模型、点云3D目标检测、目标跟踪、Occupancy、cuda与TensorRT模型部署、大模型与自动驾驶、Nerf、语义分割、自动驾驶仿真、传感器部署、决策规划、轨迹预测等多个方向学习视频（扫码即可学习）

网页端官网：www.zdjszx.com

② 国内首个自动驾驶学习社区

国内最大最专业，近3000人的交流社区，已得到大多数自动驾驶公司的认可！涉及30+自动驾驶技术栈学习路线，从0到一带你入门自动驾驶感知（2D/3D检测、语义分割、车道线、BEV感知、Occupancy、多传感器融合、多传感器标定、目标跟踪）、自动驾驶定位建图（SLAM、高精地图、局部在线地图）、自动驾驶规划控制/轨迹预测等领域技术方案、大模型、端到端等，更有行业动态和岗位发布！欢迎扫描下方二维码，加入自动驾驶之心知识星球，这是一个真正有干货的地方，与领域大佬交流入门、学习、工作、跳槽上的各类难题，日常分享论文+代码+视频

③【自动驾驶之心】技术交流群

自动驾驶之心是首个自动驾驶开发者社区，聚焦感知、定位、融合、规控、标定、端到端、仿真、产品经理、自动驾驶开发、自动标注与数据闭环多个方向，目前近60+技术交流群，欢迎加入！扫码添加汽车人助理微信邀请入群，备注：学校/公司+方向+昵称（快速入群方式）

④【自动驾驶之心】全平台矩阵