2024/06/28 by Wael Mattar, Idan Levy, Mattar, Wael +5 · 3 citations
Computer Science · Engineering · #65T60 #Advanced Image Fusion Techniques #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #I.4.10 #I.4.2 #I.4.5 #Image Retrieval and Classification Techniques #Machine Learning (cs.LG) #Medical Image Segmentation Techniques
paper · pdf · doi:10.48550/arxiv.2406.19997
openalex publication_date 2024/06/28 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
In this paper, we take a new approach to autoregressive image generation that is based on two main ingredients. The first is wavelet image coding, which allows to tokenize the visual details of an image from coarse to fine details by ordering the information starting with the most significant bits of the most significant wavelet coefficients. The second is a variant of a language transformer whose architecture is re-designed and optimized for token sequences in this 'wavelet language'. The transformer learns the significant statistical correlations within a token sequence, which are the manifestations of well-known correlations between the wavelet subbands at various resolutions. We show experimental results with conditioning on the generation process.