用循环一致关键点提升无监督RGB-D配准精度
Leveraging Cycle-Consistent Anchor Points for Self-Supervised RGB-D Registration
- 以循环一致关键点约束匹配空间一致性
- 在ScanNet和3DMatch上超越现有自监督方法
- 适合做三维场景重建与无监督视觉定位的研究者
随着消费级深度相机的普及，大量未标注的RGB-D数据涌现。如何利用这些数据进行场景几何推理成为关键问题。现有方法多依赖几何与特征相似性，本文另辟蹊径：使用循环一致的关键点作为显著点，在匹配过程中施加空间一致性约束，提升对应点精度。此外，提出一种新型姿态模块，融合GRU循环单元与变换同步机制，有效融合历史信息与多视角数据。实验表明，该方法在ScanNet和3DMatch数据集上超越已有自监督注册方法，甚至优于部分旧版有监督方法。还将所提组件集成至现有方法中，验证了其普适有效性。
原文摘要 · Abstract (English)
With the rise in consumer depth cameras, a wealth of unlabeled RGB-D data has become available. This prompts the question of how to utilize this data for geometric reasoning of scenes. While many RGB-D registration meth- ods rely on geometric and feature-based similarity, we take a different approach. We use cycle-consistent keypoints as salient points to enforce spatial coherence constraints during matching, improving correspondence accuracy. Additionally, we introduce a novel pose block that combines a GRU recurrent unit with transformation synchronization, blending historical and multi-view data. Our approach surpasses previous self- supervised registration methods on ScanNet and 3DMatch, even outperforming some older supervised methods. We also integrate our components into existing methods, showing their effectiveness.
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。