挖掘与迁移特征-几何一致性用于无监督点云配准
Mining and Transferring Feature-Geometry Coherence for Unsupervised Point Cloud Registration
AI总结：
针对无监督点云配准伪标签质量差的问题，提出INTEGER方法，通过特征-几何一致性挖掘模块结合高低层信息生成可靠伪标签，并利用基于锚点的对比学习与混合密度学生模型构建鲁棒特征空间，在KITTI和nuScenes上取得优异性能。
摘要：
点云配准作为3D视觉中的一项基础任务，在室外环境中借助基于学习的方法取得了显著成功。近期出现了无监督室外点云配准方法，以规避昂贵的位姿标注需求。然而，这些方法未能为无监督训练建立可靠的优化目标，要么依赖过强的几何假设，要么由于低层几何与高层上下文信息融合不足而产生低质量的伪标签。我们观察到，在特征空间中，潜在的新内点对应关系倾向于聚集在各自总结现有内点特征的正锚点周围。受此启发，我们提出了一种名为INTEGER的新型无监督配准方法，通过结合高层上下文信息来挖掘可靠的伪标签。具体而言，我们提出了Feature-Geometry Coherence Mining模块，在训练期间为每个小批量数据动态调整教师模型，并通过同时考虑高层特征表示和低层几何线索来发现可靠的伪标签。此外，我们提出了Anchor-Based Contrastive Learning，利用锚点促进对比学习以构建鲁棒的特征空间。最后，我们引入了Mixed-Density Student来学习密度不变特征，以应对室外场景中密度变化和低重叠度带来的挑战。在KITTI和nuScenes数据集上的大量实验表明，我们的INTEGER在准确性和泛化性方面均取得了具有竞争力的性能。
英文摘要：
Point cloud registration, a fundamental task in 3D vision, has achieved remarkable success with learning-based methods in outdoor environments. Unsupervised outdoor point cloud registration methods have recently emerged to circumvent the need for costly pose annotations. However, they fail to establish reliable optimization objectives for unsupervised training, either relying on overly strong geometric assumptions, or suffering from poor-quality pseudo-labels due to inadequate integration of low-level geometric and high-level contextual information. We have observed that in the feature space, latent new inlier correspondences tend to cluster around respective positive anchors that summarize features of existing inliers. Motivated by this observation, we propose a novel unsupervised registration method termed INTEGER to incorporate high-level contextual information for reliable pseudo-label mining. Specifically, we propose the Feature-Geometry Coherence Mining module to dynamically adapt the teacher for each mini-batch of data during training and discover reliable pseudo-labels by considering both high-level feature representations and low-level geometric cues. Furthermore, we propose Anchor-Based Contrastive Learning to facilitate contrastive learning with anchors for a robust feature space. Lastly, we introduce a Mixed-Density Student to learn density-invariant features, addressing challenges related to density variation and low overlap in the outdoor scenario. Extensive experiments on KITTI and nuScenes datasets demonstrate that our INTEGER achieves competitive performance in terms of accuracy and generalizability.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
