With the evolution of storage and communication protocols, ultra-low bitrate image
compression has become a highly demanding topic. However, all existing compression …

The last decade has seen tremendous progress in our ability to generate realistic-looking
data, be it images, text, audio, or video. Here, we discuss the closely related problem of …

Most existing image compression approaches perform transform coding in the pixel space to
reduce its spatial redundancy. However they encounter difficulties in achieving both high …

Large-scale training of latent diffusion models (LDMs) has enabled unprecedented quality in
image generation. However, the key components of the best performing LDM training …

Image compression methods based on machine learning have achieved high rate-distortion
performance. However, the reconstructions they produce suffer from blurring at extremely …

Diffusion probabilistic models have achieved mainstream success in many generative
modeling tasks, from image generation to inverse problem solving. A distinct feature of these …

While learned image compression methods have achieved impressive results in either
human visual perception or machine vision tasks, they are often specialized only for one …

This study addresses the challenge of controlling the global color aspect of images
generated by a diffusion model without training or fine-tuning. We rewrite the guidance …

Building world models that accurately and comprehensively represent the real world is the
utmost aspiration for conditional image generative models as it would enable their use as …

Despite the significant progress in recent deep learning-based image compression, the
reconstructed visual quality still suffers at low bitrates due to the lack of high-frequency …