Adversarial Video Compression Guided by Soft Edge Detection

TL;DR

This paper introduces a novel GAN-based video compression framework that utilizes soft edge detection and low-level maps, achieving higher quality at lower bitrates compared to standard codecs.

Contribution

It presents a new video compression method that trains a generative decoder on limited key frames and low-level maps, avoiding the need for extensive pre-training or interpolation.

Findings

Outperforms H.264 and HEVC at very low bitrates

Uses a soft edge detector for low-level map generation

Achieves high-quality reconstructions with limited training data

Abstract

We propose a video compression framework using conditional Generative Adversarial Networks (GANs). We rely on two encoders: one that deploys a standard video codec and another which generates low-level maps via a pipeline of down-sampling, a newly devised soft edge detector, and a novel lossless compression scheme. For decoding, we use a standard video decoder as well as a neural network based one, which is trained using a conditional GAN. Recent "deep" approaches to video compression require multiple videos to pre-train generative networks to conduct interpolation. In contrast to this prior work, our scheme trains a generative decoder on pairs of a very limited number of key frames taken from a single video and corresponding low-level maps. The trained decoder produces reconstructed frames relying on a guidance of low-level maps, without any interpolation. Experiments on a diverse set of 131 videos demonstrate that our proposed GAN-based compression engine achieves much higher quality reconstructions at very low bitrates than prevailing standard codecs such as H.264 or HEVC.