无需标定物，用深度流实现激光雷达与摄像头精准校准
UniCalib: Targetless LiDAR-Camera Calibration via Probabilistic Flow on Unified Depth Representations
- 将校准转化为深度图内一致性流动估计，统一深度表示
- 在KITTI数据集上实现0.635cm平移误差、0.045度旋转误差
- 通过可靠性图和加权损失提升关键区域对齐鲁棒性
精确的激光雷达-摄像头校准对机器人感知系统至关重要。在自动驾驶等场景中，在线无标定物校准可快速纠正因机械振动引起的传感器偏移。然而，现有方法难以有效提取激光雷达与图像间一致特征，且未关注显著区域，影响跨模态对齐鲁棒性。为此，我们提出DF-Calib，将校准重构为模态内深度流估计问题。该方法从相机图像生成稠密深度图，并补全稀疏投影的激光雷达深度图，利用共享特征编码器提取一致的深度-深度特征，有效弥合2D-3D跨模态差距。同时，引入可靠性图以优先处理有效像素，并设计感知加权稀疏光流损失以增强深度流估计。多数据集实验验证其精度与泛化能力，于KITTI数据集上达到0.635cm平均平移误差和0.045度旋转误差。
原文摘要 · Abstract (English)
Precise LiDAR-camera calibration is crucial for integrating these two sensors into robotic systems to achieve robust perception. In applications like autonomous driving, online targetless calibration enables a prompt sensor misalignment correction from mechanical vibrations without extra targets. However, existing methods exhibit limitations in effectively extracting consistent features from LiDAR and camera data and fail to prioritize salient regions, compromising cross-modal alignment robustness. To address these issues, we propose DF-Calib, a LiDAR-camera calibration method that reformulates calibration as an intra-modality depth flow estimation problem. DF-Calib estimates a dense depth map from the camera image and completes the sparse LiDAR projected depth map, using a shared feature encoder to extract consistent depth-to-depth features, effectively bridging the 2D-3D cross-modal gap. Additionally, we introduce a reliability map to prioritize valid pixels and propose a perceptually weighted sparse flow loss to enhance depth flow estimation. Experimental results across multiple datasets validate its accuracy and generalization,with DF-Calib achieving a mean translation error of 0.635cm and rotation error of 0.045 degrees on the KITTI dataset.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。