Segmenting Scenes by Matching Image Composites
NIPS(2009)
摘要
In this paper, we investigate how, given an image, similar images sharing the same global description can help with unsupervised scene segmentation. In contrast to recent work in semantic alignment of scenes, we allow an input image to be explainedbypartial matchesof similar scenes. This allows fora betterexplanation of the input scenes. We perform MRF-based segmentation that optimizes over matches,while respectingboundaryinformation. Therecoveredsegmentsarethen used to re-querya large database of images to retrieve better matches for the target regions. We show improved performance in detecting the principal occluding and contact boundaries for the scene over previous methods on data gathered from the LabelMe database.
更多查看译文
关键词
data gathering
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络