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 2106.03090cs.CV
收藏

深度匹配先验:密集对应的测试时间优化

Deep Matching Prior: Test-Time Optimization for Dense Correspondence

Korea University(高丽大学)

Sunghwan Hong, Seungryong Kim

摘要:

在视觉上或语义上相似的图像之间建立密集对应的传统技术集中在设计特定于任务的匹配先验上,这是难以建模的。为了克服这一点,最近的基于学习的方法已经尝试在大的训练数据上学习模型本身内的良好匹配先验。性能改进是明显的,但需要足够的训练数据和强化学习阻碍了它们的适用性。此外,在测试时使用固定模型并没有考虑到一对图像可能需要自己的先验知识这一事实,从而提供了有限的性能并且对看不见的图像的泛化能力较差。在本文中,我们证明了可以通过单独优化输入图像对上的未训练匹配网络来捕获特定于图像对的先验。针对这种密集对应的测试时间优化,我们提出了一个残差匹配网络和一个置信度感知的对比损失,以保证有意义的收敛。实验表明,我们的框架,被称为深度匹配先验(Deep Matching Prior,缩写为MMM),是有竞争力的,甚至优于,对最新的基于学习的方法在几个基准几何匹配和语义匹配,即使它既不需要大的训练数据,也不需要密集的学习。通过预先训练的网络,它在所有基准测试中都达到了最先进的性能。

英文摘要:

Conventional techniques to establish dense correspondences across visually or semantically similar images focused on designing a task-specific matching prior, which is difficult to model. To overcome this, recent learning-based methods have attempted to learn a good matching prior within a model itself on large training data. The performance improvement was apparent, but the need for sufficient training data and intensive learning hinders their applicability. Moreover, using the fixed model at test time does not account for the fact that a pair of images may require their own prior, thus providing limited performance and poor generalization to unseen images. In this paper, we show that an image pair-specific prior can be captured by solely optimizing the untrained matching networks on an input pair of images. Tailored for such test-time optimization for dense correspondence, we present a residual matching network and a confidence-aware contrastive loss to guarantee a meaningful convergence. Experiments demonstrate that our framework, dubbed Deep Matching Prior (DMP), is competitive, or even outperforms, against the latest learning-based methods on several benchmarks for geometric matching and semantic matching, even though it requires neither large training data nor intensive learning. With the networks pre-trained, DMP attains state-of-the-art performance on all benchmarks.

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。

↑