Tremendous advances have been achieved in image translation with the employment of generative adversarial networks (GANs). With respect to video-to-video translation, similar idea has been leveraged by various researches, which may focus on the associations among relevant frames. However, the existing video-synthesis methods based on GANs do not make full exploitation of the spatial–temporal information in videos, especially in the continuous frames. In this paper, we propose an efficient method to conduct video translation that can preserve the frame modification trends in sequential frames of the original video and smooth the variations between the generated frames. To constrain the consistency of the mentioned tendency between the generated video and the original one, we propose a tendency-invariant loss to impel further exploitation of spatial-temporal information. Experiments show that our method is able to learn more abundant information of adjacent frames and generate more desirable videos than the baselines, i.e., Recycle-GAN and CycleGAN.

中文翻译：

---

保留帧修改趋势的无监督视频到视频翻译

通过使用生成对抗网络 (GAN)，图像翻译取得了巨大进步。关于视频到视频的翻译，类似的想法已经被各种研究所利用，这些研究可能集中在相关帧之间的关联上。然而，现有的基于 GAN 的视频合成方法并没有充分利用视频中的时空信息，尤其是在连续帧中。在本文中，我们提出了一种有效的视频翻译方法，可以保留原始视频连续帧中的帧修改趋势并平滑生成帧之间的变化。为了限制生成的视频和原始视频之间提到的趋势的一致性，我们提出了一种趋势不变的损失来推动对时空信息的进一步利用。实验表明，我们的方法能够学习到更丰富的相邻帧信息并生成比基线（即 Recycle-GAN 和 CycleGAN）更理想的视频。