用模板匹配实现开放场景下的精准目标检测与分割。
From Local Matches to Global Masks: Template-Guided Instance Detection and Segmentation in Open-World Scenes
- 通过局部像素块匹配生成候选点，避免依赖不稳定的提议框。
- 在复杂遮挡和杂乱背景下，掩码召回率提升18.7%。
- 适合机器人在未知环境中识别新物体，尤其对小样本场景友好。
在开放世界环境下检测并分割新物体实例是机器人感知的基础问题。仅给定少量模板图像，机器人需在杂乱且从未见过的场景中定位并分割特定物体实例。现有基于提议的方法对提议质量高度敏感，常因遮挡和背景干扰而失效。本文提出L2G-Det框架，通过模板与查询图像间密集的像素块级匹配，直接生成候选点，再经候选筛选模块抑制误报。过滤后的点用于提示增强版Segment Anything Model（SAM），注入实例级对象标记，实现完整实例掩码的可靠重建。实验表明，在挑战性的开放世界设置下，该方法显著优于基于提议的方法。
原文摘要 · Abstract (English)
Detecting and segmenting novel object instances in open-world environments is a fundamental problem in robotic perception. Given only a small set of template images, a robot must locate and segment a specific object instance in a cluttered, previously unseen scene. Existing proposal-based approaches are highly sensitive to proposal quality and often fail under occlusion and background clutter. We propose L2G-Det, a local-to-global instance detection framework that bypasses explicit object proposals by leveraging dense patch-level matching between templates and the query image. Locally matched patches generate candidate points, which are refined through a candidate selection module to suppress false positives. The filtered points are then used to prompt an augmented Segment Anything Model (SAM) with instance-specific object tokens, enabling reliable reconstruction of complete instance masks. Experiments demonstrate improved performance over proposal-based methods in challenging open-world settings.
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。