论文标题
内窥镜检查中的超级点特征
SuperPoint features in endoscopy
论文作者
论文摘要
研究结果与常规医学实践中的适用性之间通常存在很大的差距。这项工作研究了在常规结肠镜检查过程中捕获的医学数据集中众所周知的本地特征的性能。本地功能提取和匹配是许多计算机视觉应用程序的关键步骤，特别是关于3D建模。在医疗领域中，手工制作的本地功能（例如SIFT）具有Colmap之类的公共管道，仍然是这种任务的主要工具。我们探讨了众所周知的自我监督方法超级点的潜力，为内窥镜领域提供了适应性的变化，并提出了一个具有挑战性的评估框架。基于SuperPoint的模型的匹配质量明显高于该域中常用的本地特征。我们的改编模型避免了镜面区域内的特征，这是内窥镜图像中频繁且有问题的人工制品，因此在匹配和重建结果中带来了好处。
There is often a significant gap between research results and applicability in routine medical practice. This work studies the performance of well-known local features on a medical dataset captured during routine colonoscopy procedures. Local feature extraction and matching is a key step for many computer vision applications, specially regarding 3D modelling. In the medical domain, handcrafted local features such as SIFT, with public pipelines such as COLMAP, are still a predominant tool for this kind of tasks. We explore the potential of the well known self-supervised approach SuperPoint, present an adapted variation for the endoscopic domain and propose a challenging evaluation framework. SuperPoint based models achieve significantly higher matching quality than commonly used local features in this domain. Our adapted model avoids features within specularity regions, a frequent and problematic artifact in endoscopic images, with consequent benefits for matching and reconstruction results.
