发表机构
Univ. Grenoble Alpes; CNRS; Grenoble INP–UGA; GIPSA-lab; Institut Universitaire de France (IUF); Lynred（格勒诺布尔阿尔卑斯大学; 法国国家科学研究中心; 格勒诺布尔国立理工学院; GIPSA实验室; 法国大学研究院; Lynred公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
XCalib提出一种无监督密集热红外-可见光配准框架，利用虚拟针孔相机参数化作为几何约束，结合深度估计优化位姿与内参，并通过归一化边缘相关性度量，提升动态场景下的时间稳定性和对齐精度。
AI 中文摘要
图像配准是多模态感知任务（包括图像融合、目标检测和语义分割）中的关键预处理步骤。在高级驾驶辅助系统（ADAS）中，可见光（RGB）与红外（IR）相机之间的空间错位——由光轴不重合和视场差异引起——会导致非均匀视差和视觉重影。基于关键点的经典方法局限于全局单应性变换，在动态深度下失效，而无约束的密集光流算法缺乏结构正则化，且存在时间不稳定性。本文提出XCalib，一种无监督的密集热红外-可见光配准框架，以弥合这一差距。XCalib并非作为绝对度量校准工具，而是严格将虚拟针孔相机参数化用作几何约束空间。通过优化有效相对位姿和内参以及预测的单目度量深度，XCalib将空间位移的搜索空间限制在物理有效的投影几何内。我们的主要贡献包括：（1）一种新颖的配准范式，利用相机参数化作为密集跨模态扭曲的隐式正则化器；（2）归一化边缘相关性（NEC），一种针对跨光谱对齐的鲁棒结构相似性度量；（3）在公开ADAS数据集上进行的大量定量和定性评估，展示了相对于无约束密集光流基线在时间稳定性和对齐精度上的优越性。
英文摘要
Image registration is a vital preprocessing step in multimodal perception tasks, including image fusion, object detection, and semantic segmentation. In Advanced Driver- Assistance Systems (ADAS), spatial misalignment between visible (RGB) and infrared (IR) cameras -caused by non-coincident optical axes and field-of-view differences- introduces non-uniform parallax and visual ghosting. Classical keypoint-based methods are restricted to global homographies that fail under dynamic depth, while unconstrained dense flow algorithms lack structural regularization and suffer from temporal instability. In this paper, we propose XCalib, an unsupervised dense thermal-visible registration framework that bridges this gap. Rather than serving as an absolute metric calibration tool, XCalib leverages virtual pinhole camera parameterization strictly as a geometric constraint space. By optimizing effective relative pose and intrinsics alongside predicted monocular metric depth, XCalib restricts the search space of spatial displacements to physically valid projection geometries. Our key contributions are: (1) a novel registration paradigm that uses camera parameterization as an implicit regularizer for dense cross-modal warping; (2) Normalized Edges Correlation (NEC), a robust structural similarity metric tailored to cross- spectral alignment; and (3) extensive quantitative and qualitative evaluations across public ADAS datasets, demonstrating superior temporal stability and alignment accuracy over unconstrained dense flow baselines.
Comments10 pages, 6 figures
