发表机构
Huazhong University of Science and Technology; Northwestern Polytechnical University; Delft University of Technology（华中科技大学; 西北工业大学; 代尔夫特理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对现有2D-3D对应剪枝方案受深度先验噪声影响的问题，提出Ex-Sim(3)-Reg算法，在多数据集上实现配准召回率最高24.7%的提升。
AI 中文摘要
基于学习的图像-点云（I2P）配准近年来受到越来越多的关注。然而，现有方法在具有未见、低内点或畸变等挑战性场景下仍难以应对严重的外点问题，因此亟需一种快速且鲁棒的2D-3D对应关系剪枝方法。最近，一种有前景的方案利用深度先验将2D-3D对应关系提升为3D-3D对应关系，将对应关系剪枝转化为Sim(3)配准问题。但从单目图像估计的深度先验固有地存在噪声，削弱了该方案的可靠性。本文为显式建模不可忽略的深度噪声，将对应关系剪枝重新表述为扩展Sim(3)配准问题，并提出一种简单却有效的剪枝算法Ex-Sim(3)-Reg。我们还提供理论分析以验证所提方法的有效性。在7-Scenes、RGBD-V2、ScanNet和TUM数据集上的大量实验表明，Ex-Sim(3)-Reg相较于最先进的基线方法，在配准召回率上实现了高达24.7%的提升，代码已发布至该http URL。
英文摘要
Learning-based image-to-point-cloud (I2P) registration has garnered increasing attention in recent years. Nevertheless, existing methods still struggle with severe outliers under challenging scenarios with unseen, low-inlier, or distorted cases. A fast and robust 2D-3D correspondence pruning method is therefore highly desirable. Recently, a promising scheme lifts 2D-3D correspondences to 3D-3D correspondences using depth priors, casting correspondence pruning as a Sim(3) registration problem. However, depth priors estimated from monocular images are inherently noisy, which undermines the reliability of this scheme. In this paper, to explicitly model non-negligible depth noise, we reformulate correspondence pruning as an extended Sim(3) registration problem and propose a simple yet effective pruning algorithm termed Ex-Sim(3)-Reg. We further provide a theoretical analysis to justify the effectiveness of our method. Extensive experiments on the 7-Scenes, RGBD-V2, ScanNet, and TUM datasets demonstrate that Ex-Sim(3)-Reg achieves up to \textbf{24.7\% improvement} in registration recall over state-of-the-art baseline methods. Code is released at github.com/anpei96/ex-sim3-demo
CommentsAccepted by ECCV 2026
