SinGAN-GIF: Learning a Generative Video Model from a Single GIF
SinGAN-GIF: Learning a Generative Video Model from a Single GIF
复制标题
DOI：
10.1109/wacv48630.2021.00135
复制
发表时间：
2021-01
期刊：
影响因子：
--
通讯作者：
Rajat Arora;Yong Jae Lee
中科院分区：
文献类型：
--
作者：
Rajat Arora;Yong Jae Lee
我们提出了 SinGAN-GIF，这是基于图像的 SinGAN [27] 到 GIF 或短视频片段的扩展。我们的方法学习 GIF 中图像块的分布及其运动模式。为此，我们使用 3D 和 2D 卷积网络金字塔以及图像和视频鉴别器来对时间信息进行建模，同时减少模型参数和训练时间。 SinGAN-GIF 可以为不同空间分辨率或时间帧速率的自然场景生成外观相似的视频样本，并且可以扩展到其他视频应用，如视频编辑、超分辨率和运动传输。带有补充视频结果的项目页面为：https://rajat95.github.io/singan-gif/
We propose SinGAN-GIF, an extension of the image-based SinGAN [27] to GIFs or short video snippets. Our method learns the distribution of both the image patches in the GIF as well as their motion patterns. We do so by using a pyramid of 3D and 2D convolutional networks to model temporal information while reducing model parameters and training time, along with an image and a video discriminator. SinGAN-GIF can generate similar looking video samples for natural scenes at different spatial resolutions or temporal frame rates, and can be extended to other video applications like video editing, super resolution, and motion transfer. The project page, with supplementary video results, is: https://rajat95.github.io/singan-gif/