GLASS: Geometry-aware Local Alignment and Structure Synchronization Network for 2D-3D Registration
This addresses image-to-point cloud registration for computer vision applications, representing an incremental improvement with novel modules for geometry enhancement and structural consistency.
The paper tackles the problem of 2D-3D registration in scenes with repetitive patterns, where images lack 3D structural cues and alignment with point clouds, leading to incorrect matches. The proposed method achieves state-of-the-art performance on RGB-D Scenes v2 and 7-Scenes benchmarks.
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.