AI RESEARCH

FS-I2P:A Hierarchical Focus-Sweep Registration Network with Dynamically Allocated Depth

arXiv CS.CV

ArXi:2605.07607v1 Announce Type: new Image-to-point cloud registration is often challenged by viewpoint changes, cross-modal discrepancies, and repetitive textures, which induce scale ambiguity and consequently lead to erroneous correspondences. Recent detection-free methods alleviate this issue by leveraging multi-scale features and transformer-based interactions. However, they still suffer from attention drift across layers and intra-scale inconsistencies, hindering precise registration.