无需标注数据，高效匹配低质量图像特征点
SELC: Self-Supervised Efficient Local Correspondence Learning for Low Quality Images
- 自监督训练，不依赖人工标注
- 高分辨率下效率提升2-10倍，低分辨率保持高效
- 有效抑制长期追踪中的特征漂移，适合实时系统
准确稳定的特征匹配对计算机视觉任务至关重要，尤其在同时定位与地图构建（SLAM）等应用中。现有基于学习的特征匹配方法虽在复杂时空场景中表现良好，但在特定条件下仍面临精度与计算效率的固有权衡。本文提出一种轻量级特征匹配网络，旨在建立多帧间稀疏、稳定且一致的对应关系。该方法通过混合自监督范式消除训练中对手工标注的依赖，并有效缓解特征漂移。大量实验验证了三项关键优势：(1) 方法无需外部先验知识，可无缝融入原始数据集；(2) 与当前先进深度学习方法相比，在低分辨率下保持相当计算效率，高分辨率输入下计算效率提升2-10倍；(3) 对比评估表明，所提混合自监督方案能有效抑制长期追踪中的特征漂移，同时维持图像序列间的一致表示。
原文摘要 · Abstract (English)
Accurate and stable feature matching is critical for computer vision tasks, particularly in applications such as Simultaneous Localization and Mapping (SLAM). While recent learning-based feature matching methods have demonstrated promising performance in challenging spatiotemporal scenarios, they still face inherent trade-offs between accuracy and computational efficiency in specific settings. In this paper, we propose a lightweight feature matching network designed to establish sparse, stable, and consistent correspondence between multiple frames. The proposed method eliminates the dependency on manual annotations during training and mitigates feature drift through a hybrid self-supervised paradigm. Extensive experiments validate three key advantages: (1) Our method operates without dependency on external prior knowledge and seamlessly incorporates its hybrid training mechanism into original datasets. (2) Benchmarked against state-of-the-art deep learning-based methods, our approach maintains equivalent computational efficiency at low-resolution scales while achieving a 2-10x improvement in computational efficiency for high-resolution inputs. (3) Comparative evaluations demonstrate that the proposed hybrid self-supervised scheme effectively mitigates feature drift in long-term tracking while maintaining consistent representation across image sequences.
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。