Towards image compression with perfect realism at ultra-low bitrates

arXiv:2310.10325v2 Announce Type: replace
Abstract: Image codecs are typically optimized to trade-off bitrate \vs distortion metrics. At low bitrates, this leads to compression artefacts which are easily perceptible, even when training with perceptual or adversarial losses. To improve image quality and remove dependency on the bitrate, we propose to decode with iterative diffusion models. We condition the decoding process on a vector-quantized image representation, as well as a global image description to provide additional context. We dub our model PerCo …

abstract adversarial arxiv compression cs.cv decode eess.iv image leads losses low metrics quality trade trade-off training type