arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.01103cs.CV
收藏

几何感知条件生成的半监督视点估计

Semi-supervised Viewpoint Estimation with Geometry-aware Conditional Generation

University of Edinburgh(爱丁堡大学)

Octave Mariotti, Hakan Bilen

摘要:

人们对开发可以从有限的监督中学习的计算机视觉方法越来越感兴趣。在本文中,我们考虑的问题,学习预测相机的观点,获得地面实况注释是昂贵的,需要特殊的设备,从有限数量的标记图像。我们提出了一种半监督的视点估计方法,可以学习从未标记的图像对中推断视点信息,其中两个图像的视点变化不同。特别是,我们的方法通过结合第一个图像的外观和第二个图像的视点来学习合成第二个图像。我们证明,我们的方法显着提高了监督技术,特别是在低标签制度,并优于最先进的半监督方法。

英文摘要:

There is a growing interest in developing computer vision methods that can learn from limited supervision. In this paper, we consider the problem of learning to predict camera viewpoints, where obtaining ground-truth annotations are expensive and require special equipment, from a limited number of labeled images. We propose a semi-supervised viewpoint estimation method that can learn to infer viewpoint information from unlabeled image pairs, where two images differ by a viewpoint change. In particular our method learns to synthesize the second image by combining the appearance from the first one and viewpoint from the second one. We demonstrate that our method significantly improves the supervised techniques, especially in the low-label regime and outperforms the state-of-the-art semi-supervised methods.

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。

↑