用单个视频纹理训练生成自然动态纹理的GAN模型
DTSGAN: Learning Dynamic Textures via Spatiotemporal Generative Adversarial Network
- 分层生成：从粗到精逐步合成时空纹理
- 避免模式崩溃，提升生成结果多样性
- 适合需要真实动态纹理生成的研究者
动态纹理合成旨在生成与参考视频纹理视觉相似且在时间上具有特定平稳特性的序列。本文提出一种时空生成对抗网络（DTSGAN），仅需一个动态纹理样本即可学习其运动和内容分布特征。通过从最粗尺度到最细尺度的分层生成流程，模型可生成高质量动态纹理。为避免模式崩溃，我们设计了一种新颖的数据更新策略，有效提升了生成结果的多样性。定性与定量实验表明，该模型能生成高质量动态纹理及自然运动。
原文摘要 · Abstract (English)
Dynamic texture synthesis aims to generate sequences that are visually similar to a reference video texture and exhibit specific stationary properties in time. In this paper, we introduce a spatiotemporal generative adversarial network (DTSGAN) that can learn from a single dynamic texture by capturing its motion and content distribution. With the pipeline of DTSGAN, a new video sequence is generated from the coarsest scale to the finest one. To avoid mode collapse, we propose a novel strategy for data updates that helps improve the diversity of generated results. Qualitative and quantitative experiments show that our model is able to generate high quality dynamic textures and natural motion.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。