桥接2D-3D：具有域对齐的不确定性感知分层配准网络
Bridge 2D-3D: Uncertainty-aware Hierarchical Registration Network with Domain Alignment
AI总结：
针对图像到点云配准中匹配错误与域间隙问题，提出不确定性感知分层匹配模块和对抗模态对齐模块，经实验验证其在相关基准上达最先进水平。
摘要：
图像到点云配准方法通常采用由粗到精的流水线确定刚性变换，但直接统一匹配图像块与点云块可能导致匹配时聚焦错误噪声块而忽略关键块。此外，图像与点云模态差异显著，若设计无特定改进，弥合域间隙具挑战性。为此，我们创新提出不确定性感知分层匹配模块（UHMM）与对抗模态对齐模块（AMAM）。UHMM中，我们对图像块关键信息不确定性建模，促进图像与点云特征多级融合交互；AMAM中，设计对抗方法缩小域间隙。在RGB-D Scene V2和7-Scenes基准上的大量实验与消融研究证明，该方法具优越性，是图像到点云配准任务的最先进方法。
英文摘要：
The method for image-to-point cloud registration typically determines the rigid transformation using a coarse-to-fine pipeline. However, directly and uniformly matching image patches with point cloud patches may lead to focusing on incorrect noise patches during matching while ignoring key ones. Moreover, due to the significant differences between image and point cloud modalities, it may be challenging to bridge the domain gap without specific improvements in design. To address the above issues, we innovatively propose the Uncertainty-aware Hierarchical Matching Module (UHMM) and the Adversarial Modal Alignment Module (AMAM). Within the UHMM, we model the uncertainty of critical information in image patches and facilitate multi-level fusion interactions between image and point cloud features. In the AMAM, we design an adversarial approach to reduce the domain gap between image and point cloud. Extensive experiments and ablation studies on RGB-D Scene V2 and 7-Scenes benchmarks demonstrate the superiority of our method, making it a state-of-the-art approach for image-to-point cloud registration tasks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
