SeSeCo: Selective Semantic Compression of Images

In image compression, in applications targeting extremely low bitrates (0.01 bpp), where the reconstruction distortion can be severe, it makes sense to prioritize parts of the image that are more relevant than others. In this paper, we propose a semantic compression framework that integrates user or application preferences to compress image parts based on their semantic representation. We design a guide for trained diffusion models that takes into account the preferences for describing objects with varying accuracies. We show that we are able to preserve the selected objects while also preserving the semantic and global aspect of the image without any retraining or fine-tuning.