提升图像与点云匹配精度，尤其在重复结构场景中。
GLASS: Geometry-aware Local Alignment and Structure Synchronization Network for 2D-3D Registration
- 引入几何增强模块，用法向量注入图像特征
- 构建图结构约束匹配分布，提升一致性
- 在两个基准上达到当前最优性能
图像到点云配准方法通常采用粗到精的流程，提取局部区域对应关系并细化为密集的像素-点匹配。然而，在具有重复模式的场景中，图像往往缺乏足够的三维结构线索，难以与点云对齐，导致错误匹配。此外，现有方法普遍忽视结构一致性，限制了对应关系的充分挖掘。为此，我们提出两个新模块：局部几何增强（LGE）模块和图分布一致性（GDC）模块。LGE通过法向量增强图像与点云特征，将几何结构注入图像特征以减少误匹配。GDC从匹配点构建图结构，更新特征并显式约束相似性分布。在RGB-D Scenes v2和7-Scenes两个基准上的大量实验与消融分析表明，该方法在图像-点云配准任务中达到当前最优性能。
原文摘要 · Abstract (English)
Image-to-point cloud registration methods typically follow a coarse-to-fine pipeline, extracting patch-level correspondences and refining them into dense pixel-to-point matches. However, in scenes with repetitive patterns, images often lack sufficient 3D structural cues and alignment with point clouds, leading to incorrect matches. Moreover, prior methods usually overlook structural consistency, limiting the full exploitation of correspondences. To address these issues, we propose two novel modules: the Local Geometry Enhancement (LGE) module and the Graph Distribution Consistency (GDC) module. LGE enhances both image and point cloud features with normal vectors, injecting geometric structure into image features to reduce mismatches. GDC constructs a graph from matched points to update features and explicitly constrain similarity distributions. Extensive experiments and ablations on two benchmarks, RGB-D Scenes v2 and 7-Scenes, demonstrate that our approach achieves state-of-the-art performance in image-to-point cloud registration.
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。