Adversarial Video Compression Guided by Soft Edge Detection
This addresses video compression for applications requiring low bitrates, offering a novel method that improves quality over existing standards.
The paper tackles video compression by proposing a GAN-based framework that uses two encoders and a neural decoder trained on key frames from a single video, achieving higher quality reconstructions at very low bitrates compared to standard codecs like H.264 or HEVC, as demonstrated on 131 videos.
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.