不依赖描述子的特征点检测，通过金字塔结构与一致性匹配提升效率
FPC-Net: Revisiting SuperPoint with Descriptor-Free Keypoint Detection via Feature Pyramids and Consistency-Based Implicit Matching
- 基于特征金字塔与隐式一致性匹配实现无描述子特征点检测
- 相比传统方法匹配精度略低但内存占用大幅减少
- 适合对内存敏感的实时定位系统，尤其适用于边缘设备
兴趣点的提取与匹配是几何计算机视觉任务的基础。传统方法为每个兴趣点分配描述子，并依据描述子相似性进行对应关系识别。本文提出一种新方法，在特征点检测阶段即内置匹配关联，无需计算、存储、传输或匹配描述子。尽管匹配精度略低于传统方法，但完全省去描述子环节，显著降低定位系统的内存开销。我们通过与经典手工设计方法及现代学习型方法对比，验证了该方法的有效性。
原文摘要 · Abstract (English)
The extraction and matching of interest points are fundamental to many geometric computer vision tasks. Traditionally, matching is performed by assigning descriptors to interest points and identifying correspondences based on descriptor similarity. This work introduces a technique where interest points are inherently associated during detection, eliminating the need for computing, storing, transmitting, or matching descriptors. Although the matching accuracy is marginally lower than that of conventional approaches, our method completely eliminates the need for descriptors, leading to a drastic reduction in memory usage for localization systems. We assess its effectiveness by comparing it against both classical handcrafted methods and modern learned approaches.
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。