Text + Sketch: Image Compression at Ultra Low Rates
This addresses the challenge of efficient image compression for applications requiring minimal data usage, though it is incremental as it builds on existing generative models.
The paper tackles the problem of image compression at ultra low bit-rates by adapting pre-trained text-to-image generative models, showing that using text descriptions with side information can significantly improve perceptual and semantic fidelity compared to learned compressors without end-to-end training.
Recent advances in text-to-image generative models provide the ability to generate high-quality images from short text descriptions. These foundation models, when pre-trained on billion-scale datasets, are effective for various downstream tasks with little or no further training. A natural question to ask is how such models may be adapted for image compression. We investigate several techniques in which the pre-trained models can be directly used to implement compression schemes targeting novel low rate regimes. We show how text descriptions can be used in conjunction with side information to generate high-fidelity reconstructions that preserve both semantics and spatial structure of the original. We demonstrate that at very low bit-rates, our method can significantly improve upon learned compressors in terms of perceptual and semantic fidelity, despite no end-to-end training.