无需训练，用光影变化实现精准图像分割
Image Segmentation from Shadow-Hints using Minimum Spanning Trees
- 利用多角度光照下的图像序列，通过最小生成树提取阴影线索
- 在无标注数据下达到与训练模型相当的分割效果
- 适合缺乏标注数据的场景，如医学影像或工业检测
RGB空间中的图像分割是一项长期挑战，当前最先进的方法依赖数以千计甚至百万张带标注图像进行训练。尽管性能优异，但仍不完美。本文提出一种新颖的图像分割方法，在无需训练的前提下实现相近的分割质量。该方法仅需一个静止相机和单一光源在不同位置拍摄的图像序列，类似于光度立体技术所用的数据采集方式。通过分析阴影变化，结合最小生成树算法提取形状线索，从而实现像素级分割。整个过程不依赖标注数据，显著降低了对大规模标注资源的依赖。
原文摘要 · Abstract (English)
Image segmentation in RGB space is a notoriously difficult task where state-of-the-art methods are trained on thousands or even millions of annotated images. While the performance is impressive, it is still not perfect. We propose a novel image segmentation method, achieving similar segmentation quality but without training. Instead, we require an image sequence with a static camera and a single light source at varying positions, as used in for photometric stereo, for example.
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。