两篇新研究论文介绍了通过更有效地集成激光雷达和相机数据来增强自动驾驶中三维目标检测的新方法。DeGuNet提出了一种专为深度引导学习设计的超紧凑图像骨干网络，将内存消耗降低高达66.5%，并提高推理速度，同时提升mAP增益。ViCo3D利用DINOv2等视觉基础模型从激光雷达数据中提取更丰富的语义先验，改善车联网系统中的协同感知，并取得最先进的成果。 AI
影响 这些在高效和协同三维感知方面的进步可以加速更强大的自动驾驶系统的开发和部署。
排序理由 arXiv上发表的两篇研究论文，介绍了三维目标检测的新方法。
AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2607.12419v1 Announce Type: new Abstract: In autonomous driving perception, the fusion of LiDAR and camera modalities has become the dominant paradigm for 3D object detection. However, current multi-modal frameworks heavily rely on massive visual backbones pretrained on 2D …
arXiv:2607.12959v1 Announce Type: new Abstract: LiDAR-based collaborative 3D perception in Vehicle-to-Everything (V2X) systems typically relies on fusing bird's-eye-view (BEV) features across agents. However, current BEV representations, typically extracted by LiDAR backbones tra…
LiDAR-based collaborative 3D perception in Vehicle-to-Everything (V2X) systems typically relies on fusing bird's-eye-view (BEV) features across agents. However, current BEV representations, typically extracted by LiDAR backbones trained from scratch, are geometry-dominated and la…
In autonomous driving perception, the fusion of LiDAR and camera modalities has become the dominant paradigm for 3D object detection. However, current multi-modal frameworks heavily rely on massive visual backbones pretrained on 2D semantic tasks. This reliance introduces substan…