Generative Adversarial Networks for Extreme Learned Image Compression
We present a learned image compression system based on GANs, operating at extremely low bitrates. Our proposed framework combines an encoder, decoder/generator and a multi-scale discriminator, which we train jointly for a generative learned compression objective. The model synthesizes details it cannot afford to store, obtaining visually pleasing results at bitrates where previous methods fail and show strong artifacts. Furthermore, if a semantic label map of the original image is available, our method can fully synthesize unimportant regions in the decoded image such as streets and trees from the label map, proportionally reducing the storage cost. A user study confirms that for low bitrates, our approach is preferred to state-of-the-art methods, even when they use more than double the bits.
Code (1)
Tasks
DecoderImage CompressionSimilar Papers 제목 키워드 기반
Fidelity-Controllable Extreme Image Compression with Generative Adversarial Networks
We propose a GAN-based image compression method working at extremely low bitrates below 0.1bpp. Most existing learned image compression methods suffer from blur at extremely low bitrates. Although GAN can help to reconst…
Image CompressionAdversarial Distortion for Learned Video Compression
In this paper, we present a novel adversarial lossy video compression model. At extremely low bit-rates, standard video coding schemes suffer from unpleasant reconstruction artifacts such as blocking, ringing etc. Existi…
BlockingMS-SSIMSSIMVideo CompressionExtreme Image Coding via Multiscale Autoencoders With Generative Adversarial Optimization
We propose a MultiScale AutoEncoder(MSAE) based extreme image compression framework to offer visually pleasing reconstruction at a very low bitrate. Our method leverages the "priors" at different resolution scale to impr…
Generative Adversarial NetworkImage CompressionHow to Exploit the Transferability of Learned Image Compression to Conventional Codecs
Lossy image compression is often limited by the simplicity of the chosen loss measure. Recent research suggests that generative adversarial networks have the ability to overcome this limitation and serve as a multi-modal…
Generative Adversarial NetworkImage CompressionMS-SSIMSSIMExtreme Video Compression with Pre-trained Diffusion Models
Diffusion models have achieved remarkable success in generating high quality image and video data. More recently, they have also been used for image compression with high perceptual quality. In this paper, we present a n…
DecoderImage CompressionVideo Compression