解决图像与点云匹配中的通道差异和冗余问题，提升注册精度。
CA-I2P: Channel-Adaptive Registration Network with Global Optimal Selection
- 引入通道自适应模块，优化图像与点云特征表达
- 采用全局最优选择机制，避免局部误匹配
- 在两个数据集上达到当前最佳性能，适合多模态感知任务
无检测方法通常采用粗到精流程，提取图像与点云特征进行块级匹配，并细化密集像素-点对应关系。然而，图像与点云间特征通道注意力差异会导致匹配效果下降，影响注册精度；此外，场景中相似结构易引发跨模态匹配的冗余对应。为此，本文提出通道自适应调节模块（CAA）和全局最优选择模块（GOS）。CAA增强模态内特征并抑制跨模态敏感性，GOS以全局优化替代局部选择。在RGB-D Scenes V2和7-Scenes数据集上的实验表明，所提方法显著优于现有技术，实现了图像到点云注册的最先进性能。
原文摘要 · Abstract (English)
Detection-free methods typically follow a coarse-to-fine pipeline, extracting image and point cloud features for patch-level matching and refining dense pixel-to-point correspondences. However, differences in feature channel attention between images and point clouds may lead to degraded matching results, ultimately impairing registration accuracy. Furthermore, similar structures in the scene could lead to redundant correspondences in cross-modal matching. To address these issues, we propose Channel Adaptive Adjustment Module (CAA) and Global Optimal Selection Module (GOS). CAA enhances intra-modal features and suppresses cross-modal sensitivity, while GOS replaces local selection with global optimization. Experiments on RGB-D Scenes V2 and 7-Scenes demonstrate the superiority of our method, achieving state-of-the-art performance in image-to-point cloud registration.
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。