Conditional Hallucinations for Image Compression

In lossy image compression, models face the challenge of either hallucinating details or generating out-of-distribution samples due to the information bottleneck. This implies that at times, introducing hallucinations is necessary to generate in-distribution samples. The optimal level of hallucination varies depending on image content, as humans are sensitive to small changes that alter the semantic meaning. We propose a novel compression method that dynamically balances the degree of hallucination based on content. We collect data and train a model to predict user preferences on hallucinations. By using this prediction to adjust the perceptual weight in the reconstruction loss, we develop a Conditionally Hallucinating compression model (ConHa) that outperforms state-of-the-art image compression methods. Code and images are available atthis https URL.

@article{aczel2025_2410.19493,
  title={ Conditional Hallucinations for Image Compression },
  author={ Till Aczel and Roger Wattenhofer },
  journal={arXiv preprint arXiv:2410.19493},
  year={ 2025 }
}