In this paper, we explore an interesting question of what can be obtained from an $8\times8$ pixel video sequence. Surprisingly, it turns out to be quite a lot. We show that when we process this $8\times8$ video with the right set of audio and image priors, we can obtain a full-length, $256\times256$ video. We achieve this $32\times$ scaling of an extremely low-resolution input using our novel audio-visual upsampling network. The audio prior helps to recover the elemental facial details and precise lip shapes and a single high-resolution target identity image prior provides us with rich appearance details. Our approach is an end-to-end multi-stage framework. The first stage produces a coarse intermediate output video that can be then used to animate single target identity image and generate realistic, accurate and high-quality outputs. Our approach is simple and performs exceedingly well (an $8\times$ improvement in FID score) compared to previous super-resolution methods. We also extend our model to talking-face video compression, and show that we obtain a $3.5\times$ improvement in terms of bits/pixel over the previous state-of-the-art. The results from our network are thoroughly analyzed through extensive ablation experiments (in the paper and supplementary material). We also provide the demo video along with code and models on our website: \url{http://cvit.iiit.ac.in/research/projects/cvit-projects/talking-face-video-upsampling}.
翻译:在本文中, 我们探索了一个有趣的问题, 从 8\ times8$ 像素视频序列中可以获得什么。 令人惊讶的是, 它被证明是相当多的。 我们显示, 当我们处理这个8\ time8$的视频时, 并配有一套正确的音频和图像前置, 我们可以得到一个全长的, 256\ times256$的视频。 我们通过我们的新视听上映网络, 实现了一个非常低分辨率输入的32\time$的缩放。 之前的音频有助于恢复元素面部细节和精确的嘴唇形状, 之前的单高分辨率目标图像为我们提供了丰富的外观细节。 我们的方法是一个端到端的多阶段框架。 我们的方法是一个粗糙的中间输出视频视频视频视频视频, 然后用来模拟单一目标身份图像, 产生现实、准确和高质量的输出。 我们的方法简单, 与以往的超级解析方法相比, 我们的平面平面图像缩缩图比模型, 并显示我们从前一线/ 的网络/ 直径路路路路段/ 的模型 改进结果 。