Dynamic texture (DT) exhibits statistical stationarity in the spatial domain and stochastic repetitiveness in the temporal dimension, indicating that different frames of DT possess a high similarity correlation that is critical prior knowledge. However, existing methods cannot effectively learn a promising synthesis model for high-dimensional DT from a small number of training data. In this paper, we propose a novel DT synthesis method, which makes full use of similarity prior knowledge to address this issue. Our method bases on the proposed kernel similarity embedding, which not only can mitigate the high-dimensionality and small sample issues, but also has the advantage of modeling nonlinear feature relationship. Specifically, we first raise two hypotheses that are essential for DT model to generate new frames using similarity correlation. Then, we integrate kernel learning and extreme learning machine into a unified synthesis model to learn kernel similarity embedding for representing DT. Extensive experiments on DT videos collected from the internet and two benchmark datasets, i.e., Gatech Graphcut Textures and Dyntex, demonstrate that the learned kernel similarity embedding can effectively exhibit the discriminative representation for DT. Accordingly, our method is capable of preserving the long-term temporal continuity of the synthesized DT sequences with excellent sustainability and generalization. Meanwhile, it effectively generates realistic DT videos with fast speed and low computation, compared with the state-of-the-art methods. The code and more synthesis videos are available at our project page https://shiming-chen.github.io/Similarity-page/Similarit.html.
翻译:动态纹理(DT) 显示空间域的统计性和时间层面的重复性,表明不同的DT框架具有高度相似性相关性,这是以前的关键知识。然而,现有方法无法有效地从少量的培训数据中学习高维DT的有希望的综合模型。在本文件中,我们提出一个新的DT合成方法,充分利用先前知识的相似性来解决这一问题。我们在拟议的内核嵌入中的方法基础不仅能够减轻高维度和小样本问题,而且具有建模非线性视频关系的优势。具体地说,我们首先提出对DT模式至关重要的两个假设,以便利用相似性相关数据生成新的框架。然后,我们将内核学习和极端学习机纳入一个统一的合成模型,以学习在代表DT的内核嵌入的相似性。我们从互联网和两个现实化数据集中收集的DT视频的广泛实验,即Gatech Statech Stregcculture Streutures and Dyntex, 展示了我们所学的低基内径性非线性视频的模型, 并有效保持了我们具有可持续性的Sdeal-deal-deal develilation delismal lading Scild Sp 和Sdestreptionaldeal delviews ex 。我们可有效展示了常规的实验室-delviductionalalalal 和持续性平流法。可以有效地展示了我们总制成的系统,可以有效地展示和制成的实验室-deal-delismlation-deal-develild 。可以有效地展示了常规化、制成。