提出一种更鲁棒的2D-3D对应关系学习方法，提升点云配准精度。
MinCD-PnP: Learning 2D-3D Correspondences with Approximate Blind PnP
- 用近似盲PnP替代传统微分PnP，降低对噪声和离群点的敏感度。
- 在多个数据集上实现更高的内点率和配准召回率，跨场景表现优异。
- 轻量级模块可无缝集成到现有配准网络中，适合实际应用部署。
图像到点云（I2P）配准是计算机视觉中的基础问题，旨在建立图像与点云之间的2D-3D对应关系。微分透视-点（PnP）方法通过施加投影约束来监督I2P网络，但对预测对应关系中的噪声和离群点高度敏感，影响对应关系学习效果。受盲PnP对噪声和离群点鲁棒性的启发，本文提出一种基于近似盲PnP的对应关系学习方法。为降低盲PnP的高计算成本，将问题简化为最小化学习得到的2D与3D关键点之间的Chamfer距离，称为MinCD-PnP。为此设计了轻量级多任务学习模块MinCD-Net，可轻松嵌入现有I2P配准架构。在7-Scenes、RGBD-V2、ScanNet及自采集数据集上的大量实验表明，MinCD-Net优于当前最先进方法，在跨场景和跨数据集设置下均实现了更高的内点率（IR）和配准召回率（RR）。
原文摘要 · Abstract (English)
Image-to-point-cloud (I2P) registration is a fundamental problem in computer vision, focusing on establishing 2D-3D correspondences between an image and a point cloud. The differential perspective-n-point (PnP) has been widely used to supervise I2P registration networks by enforcing the projective constraints on 2D-3D correspondences. However, differential PnP is highly sensitive to noise and outliers in the predicted correspondences. This issue hinders the effectiveness of correspondence learning. Inspired by the robustness of blind PnP against noise and outliers in correspondences, we propose an approximated blind PnP based correspondence learning approach. To mitigate the high computational cost of blind PnP, we simplify blind PnP to an amenable task of minimizing Chamfer distance between learned 2D and 3D keypoints, called MinCD-PnP. To effectively solve MinCD-PnP, we design a lightweight multi-task learning module, named as MinCD-Net, which can be easily integrated into the existing I2P registration architectures. Extensive experiments on 7-Scenes, RGBD-V2, ScanNet, and self-collected datasets demonstrate that MinCD-Net outperforms state-of-the-art methods and achieves a higher inlier ratio (IR) and registration recall (RR) in both cross-scene and cross-dataset settings.
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。