解决2D-3D匹配中的异常点问题，提升鲁棒性
Ex-Sim(3)-Reg: 2D-3D Correspondence Pruning via Extended Sim(3) Registration
- 将2D-3D对应关系转换为扩展Sim(3)注册问题，显式建模深度噪声
- 在多个数据集上实现最高24.7%的注册召回率提升
- 适合做图像与点云配准的研究者和工程师参考
基于学习的图像到点云（I2P）配准近年来受到越来越多关注。然而，现有方法在面对未见场景、低内点率或形变情况时仍受严重异常点影响。因此，亟需一种快速且鲁棒的2D-3D对应关系剪枝方法。近期一种有前景的方法利用深度先验将2D-3D对应关系提升至3D-3D对应关系，将剪枝问题转化为Sim(3)配准问题。但单目图像估计的深度先验本身存在噪声，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构建成扩展Sim(3)注册问题，并提出一种简单有效的剪枝算法Ex-Sim(3)-Reg。我们进一步提供了理论分析以证明方法有效性。在7-Scenes、RGBD-V2、ScanNet和TUM等多个数据集上的大量实验表明，Ex-Sim(3)-Reg相较于最先进基线方法，注册召回率最高提升24.7%。代码已开源至github.com/anpei96/ex-sim3-demo。
原文摘要 · Abstract (English)
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
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。