通过不确定性建模与域对齐，提升图像到点云配准精度。
Bridge 2D-3D: Uncertainty-aware Hierarchical Registration Network with Domain Alignment
- 引入不确定性感知的分层匹配模块，聚焦关键特征。
- 在RGB-D Scene V2和7-Scenes上达到最新性能，误差更低。
- 适合需要高精度配准的3D视觉任务，如机器人导航。
图像到点云配准通常采用粗到精的流程，但直接均匀匹配图像块与点云块可能导致关注噪声区域而忽略关键区域。由于图像与点云模态差异大，跨域差距难以弥合。为此，本文提出不确定性感知的分层匹配模块（UHMM）与对抗性模态对齐模块（AMAM）。UHMM建模图像块中关键信息的不确定性，促进图像与点云特征的多层级融合交互；AMAM采用对抗策略降低图像与点云间的域差距。在RGB-D Scene V2和7-Scenes基准上的大量实验与消融研究验证了该方法的优越性，使其成为当前图像到点云配准任务的领先方案。
原文摘要 · Abstract (English)
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.
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。