发表机构
Ajou University; Kennesaw State University（韩国亚洲大学; 肯尼索州立大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究自动驾驶系统中雷达-相机深度估计问题，提出单阶段JustDepth方法，仅用雷达、相机和单扫描激光雷达训练，能聚合雷达回波解耦运行时与点数，融合模态传播深度，减轻条纹伪影，相比先进方法减少推理时间并降低条纹伪影。
AI 中文摘要
在自动驾驶系统中，准确且低延迟的深度对于雷达-相机感知至关重要。相机能提供丰富外观但缺乏度量尺度，汽车雷达能提供度量范围但稀疏且有噪声。许多方法是多阶段的或依赖辅助标注，增加了延迟并限制了便携性。我们引入JustDepth，一种仅用雷达、相机和单扫描激光雷达训练的单阶段雷达-相机深度估计器。将所有雷达回波聚合为固定宽度的一维表示，使运行时与点数解耦。通过高度融合块融合模态，用轻量级GNN全局传播深度，用仅训练时的置信度解码器稳定学习且测试时无成本。通过简单增强减轻条纹伪影并用垂直-水平梯度比（VHGR）量化。在nuScenes上，与近期先进方法相比，JustDepth保持精度的同时将推理时间减少39.7倍，将条纹伪影减少66%（以VHGR衡量）。
英文摘要
Accurate yet low-latency depth is essential for radar-camera perception in autonomous systems. Cameras provide rich appearance but lack metric scale, whereas automotive radar offers metric range but is sparse and noisy. Many pipelines are multi-stage or depend on auxiliary annotations, increasing latency and limiting portability. We introduce JustDepth, a single-stage radar-camera depth estimator trained only with radar, camera, and single-scan LiDAR. All radar returns are aggregated into a fixed-width 1D representation, decoupling runtime from point count. A Height Fusion Block fuses modalities, a lightweight GNN propagates depth globally, and a training-only confidence decoder stabilizes learning with zero test-time cost. We mitigate stripe artifacts via simple augmentations and quantify them using the Vertical-Horizontal Gradient Ratio (VHGR). On nuScenes, compared to recent state-of-the-art methods, JustDepth maintains accuracy while reducing inference time by 39.7x and stripe artifacts by 66% as measured by VHGR.
CommentsProject page: https://github.com/TPyun/JustDepth
Journal refIEEE Robotics and Automation Letters ( Volume: 11, Issue: 3, March 2026)
