Hg-I2P：基于异构图打通模态以实现可泛化的图像到点云配准
Hg-I2P: Bridging Modalities for Generalizable Image-to-Point-Cloud Registration via Heterogeneous Graphs
用异构图把分割后的 2D/3D 区域作为节点、跨模态关系作为边，统一完成特征交互与对应关系剪枝，可直接迁移到图像-点云配准、跨模态定位等需要鲁棒 2D-3D 对应的任务。
原文依据 modeling the consistency among vertices and edges within the graph enables pruning of unreliable correspondences
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论图像到点云（I2P）配准旨在通过建立可靠的 2D-3D 对应关系，将 2D 图像与 3D 点云对齐。图像与点云之间巨大的模态差异使得学习兼具判别性与泛化性的特征十分困难，导致在未见场景中性能严重下降。为应对这一挑战，我们引入异构图，使得能够在统一架构内同时精化跨模态特征与对应关系。所提出的图表示分割后的 2D 与 3D 区域之间的映射，增强了跨模态特征交互，从而提升特征判别性。此外，对图中顶点与边之间一致性的建模能够剪枝不可靠的对应关系。基于上述思路，我们提出一种嵌入异构图的 I2P 配准方法，称为 Hg-I2P。该方法通过挖掘多路径特征关系来学习异构图，在异构边的引导下自适应调整特征，并利用基于图的投影一致性剪枝对应关系。在跨域设置下的六个室内与室外基准上的实验表明，Hg-I2P 在泛化性与精度上均显著优于现有方法。代码发布于 https://github.com/anpei96/hg-i2p-demo。
英文原文摘要 1343 字符
Image-to-point-cloud (I2P) registration aims to align 2D images with 3D point clouds by establishing reliable 2D-3D correspondences. The drastic modality gap between images and point clouds makes it challenging to learn features that are both discriminative and generalizable, leading to severe performance drops in unseen scenarios. We address this challenge by introducing a heterogeneous graph that enables refining both cross-modal features and correspondences within a unified architecture. The proposed graph represents a mapping between segmented 2D and 3D regions, which enhances cross-modal feature interaction and thus improves feature discriminability. In addition, modeling the consistency among vertices and edges within the graph enables pruning of unreliable correspondences. Building on these insights, we propose a heterogeneous graph embedded I2P registration method, termed Hg-I2P. It learns a heterogeneous graph by mining multi-path feature relationships, adapts features under the guidance of heterogeneous edges, and prunes correspondences using graph-based projection consistency. Experiments on six indoor and outdoor benchmarks under cross-domain setups demonstrate that Hg-I2P significantly outperforms existing methods in both generalization and accuracy. Code is released on https://github.com/anpei96/hg-i2p-demo.