Video-to-Video Synthesis

TL;DR

This paper introduces a novel generative adversarial network framework for high-resolution, temporally coherent video synthesis from various input formats, significantly advancing the quality and length of synthesized videos.

Contribution

The paper presents a new video-to-video synthesis method with specialized architectures and a spatio-temporal adversarial loss, enabling high-resolution, realistic, and coherent videos from diverse inputs.

Findings

Achieves 2K resolution videos of street scenes up to 30 seconds long.

Outperforms existing methods on multiple benchmarks.

Effective for future video prediction tasks.

Abstract

We study the problem of video-to-video synthesis, whose goal is to learn a mapping function from an input source video (e.g., a sequence of semantic segmentation masks) to an output photorealistic video that precisely depicts the content of the source video. While its image counterpart, the image-to-image synthesis problem, is a popular topic, the video-to-video synthesis problem is less explored in the literature. Without understanding temporal dynamics, directly applying existing image synthesis approaches to an input video often results in temporally incoherent videos of low visual quality. In this paper, we propose a novel video-to-video synthesis approach under the generative adversarial learning framework. Through carefully-designed generator and discriminator architectures, coupled with a spatio-temporal adversarial objective, we achieve high-resolution, photorealistic, temporally coherent video results on a diverse set of input formats including segmentation masks, sketches, and poses. Experiments on multiple benchmarks show the advantage of our method compared to strong baselines. In particular, our model is capable of synthesizing 2K resolution videos of street scenes up to 30 seconds long, which significantly advances the state-of-the-art of video synthesis. Finally, we apply our approach to future video prediction, outperforming several state-of-the-art competing systems.