ai.hackcv
论文精选 60arXiv

4DR360: State Reasoning for Joint 3D Detection and Occupancy Prediction in 4D Radar-Camera Full-Scene Perception

Reliable autonomous driving requires full-scene perception that couples foreground objects with dense semantic layout. Recently, 4D millimeter-wave radar has emerged as a robust and affordable sensor, yet its sparse returns make radar-camera fusion necessary for comprehensive scene understanding. Existing radar-camera methods mainly optimize detection, while dual-task systems usually decode boxes and occupancy with limited interaction. To address this gap and advance radar-based multi-task learning, we propose \method, a 4D radar-camera framework for 360$^\circ$ full-scene perception, which models semantic occupancy as a persistent scene state rather than a terminal output. \method{} follows a cross-modal state reasoning paradigm, where the occupancy state is modeled and propagated through stages for coarse-to-fine feature aggregation. Specifically, State-guided BEV Enhancement (SBE) strengthens intra-frame BEV representation, while Doppler-guided Temporal Fusion (DTF) preserves state evidence over longer temporal horizons. Beyond the model, we further extend ManTruckScenes with satellite-map-based generated occupancy labels and pair it with OmniHD-Scenes in a unified cross-dataset detection-and-occupancy protocol. The resulting experiments cover accuracy, robustness, ablation, and efficiency under one radar-camera multi-task evaluation framework. Code and labels will be released upon acceptance.

AI 解读论文

4DR360:结合4D雷达和相机的360度全场景感知,优化3D检测和占用预测

核心方法
提出4DR360框架,通过跨模态状态推理,将占用状态作为持续的场景状态建模,包括状态引导的BEV增强和多普勒引导的时序融合
适合谁读
研究者、工程师
要解决的问题
现有雷达-相机融合方法主要关注检测优化,未能充分实现3D检测与占用预测之间的强交互
关键实验
实验涵盖准确性、鲁棒性、消融实验和效率测试
主要贡献
扩展ManTruckScenes数据集,增加卫星地图生成的占用标签,并与OmniHD-Scenes结合,建立统一的多任务评估框架
意义与局限
提高了基于雷达的多任务学习系统的整体性能和鲁棒性,但可能面临计算资源的更高需求
领域:cs.CV作者:Xiaokai Bai、Lianqing Zheng、Runwei Guan
相关推荐
论文精选 60已解读

Principia: Relational Physics Tests for Video Models· Principia:视频模型的物理测试

Evaluating physical reasoning in video models is difficult because absolute motion measure…

领域:cs.CV作者:Varun Varma Thozhiyoor、Shivam Tripathi、Venkatesh Babu Radhakrishnan
📎 arXiv🕒 09-04 01:59🔗 arxiv.org

本站内容由 LLM 精选聚合,原文版权归 arXiv 所有 · 摘录仅供参考