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

TL;DR

This paper introduces FS-I2P, a hierarchical registration network employing a focus-sweep paradigm and dynamic layer allocation to improve image-to-point cloud registration accuracy.

Contribution

It proposes a novel focus-sweep interaction module and a dynamic layer allocation strategy, enhancing multi-scale feature association and robustness in registration tasks.

Findings

Achieves state-of-the-art performance on RGB-D Scenes V2 and 7-Scenes benchmarks.

Effectively mitigates attention drift and intra-scale inconsistencies in registration.

Demonstrates improved robustness and accuracy over existing methods.

Abstract

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. Inspired by human behavior, we propose a ``Focus--Sweep'' paradigm and develop a Hierarchical Focus--Sweep Interaction Module within an SSM-based framework to enhance multi-level cross-modal feature association. In addition, we introduce a Dynamic Layer Allocation Strategy that adaptively determines the iteration depth to better exploit geometric constraints and improve matching robustness. Extensive experiments and ablations on two benchmarks, RGB-D Scenes V2 and 7-Scenes, demonstrate that our approach achieves state-of-the-art performance.