arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1908.10543cs.CV
收藏

SPair-71 k:一个大规模的语义对应基准

SPair-71k: A Large-scale Benchmark for Semantic Correspondence

POSTECH(浦项科技大学);NPRC(神经处理研究中心);Inria(法国国家信息与自动化研究所);DI ENS(巴黎高等师范学院计算机系)

Juhong Min, Jongmin Lee, Jean Ponce, Minsu Cho

摘要:

在大的类内变化下建立视觉对应,这通常被称为语义对应或语义匹配,仍然是计算机视觉中具有挑战性的问题。然而,尽管其重要性,大多数语义对应的数据集仅限于具有相似视点和尺度的少量图像对。在本文中,我们提出了一个新的语义配对图像的大规模基准数据集SPair-71 k,其中包含70,958个图像对,这些图像对具有不同的视角和尺度。与以前的数据集相比,它在数量上明显更大,并且包含更准确和更丰富的注释。我们相信这个数据集将为研究语义对应问题提供一个可靠的测试平台,并将有助于推进这一领域的研究。我们提供了新数据集上最近方法的结果,作为进一步研究的基线。我们的基准可以在http://cvlab.postech.ac.kr/research/SPair-71k/上在线获得。

英文摘要:

Establishing visual correspondences under large intra-class variations, which is often referred to as semantic correspondence or semantic matching, remains a challenging problem in computer vision. Despite its significance, however, most of the datasets for semantic correspondence are limited to a small amount of image pairs with similar viewpoints and scales. In this paper, we present a new large-scale benchmark dataset of semantically paired images, SPair-71k, which contains 70,958 image pairs with diverse variations in viewpoint and scale. Compared to previous datasets, it is significantly larger in number and contains more accurate and richer annotations. We believe this dataset will provide a reliable testbed to study the problem of semantic correspondence and will help to advance research in this area. We provide the results of recent methods on our new dataset as baselines for further research. Our benchmark is available online at http://cvlab.postech.ac.kr/research/SPair-71k/.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑