提出分层聚焦-扫视机制，提升图像与点云配准精度。
FS-I2P:A Hierarchical Focus-Sweep Registration Network with Dynamically Allocated Depth
- 采用分层聚焦-扫视模块增强跨模态特征关联
- 动态分配迭代深度，显著提升匹配鲁棒性
- 在两个基准上达到最新水平，适合三维重建场景
图像到点云的配准常受视角变化、跨模态差异和重复纹理影响，导致尺度模糊并引发错误对应。现有无检测方法虽利用多尺度特征与基于Transformer的交互缓解该问题，但仍存在层间注意力漂移和同尺度内不一致性，限制了配准精度。受人类行为启发，我们提出“聚焦-扫视”范式，并在SSM框架中设计分层聚焦-扫视交互模块，以强化多层级跨模态特征关联。此外，引入动态层分配策略，自适应确定迭代深度，更好利用几何约束，提升匹配鲁棒性。在两个基准数据集RGB-D Scenes V2和7-Scenes上的大量实验与消融分析表明，本方法实现当前最优性能。
原文摘要 · Abstract (English)
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.
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。