2025/03/14 by Tiantian Li, Li, Tiantian, Qunbing Xia +6 · 1 citation
Computer Science · #Advanced Data Compression Techniques #Advanced Image Processing Techniques #Arithmetic coding #Compression (physics) #Compression artifact #Computer Vision and Pattern Recognition (cs.CV) #Data compression #FOS: Computer and information sciences #FOS: Electrical engineering #Generative Adversarial Networks and Image Synthesis #Image and Video Processing (eess.IV) #Image compression #Lossless compression #Lossy compression #Raster graphics #Residual #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2503.11231
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2025/03/14 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Learning-based lossless image compression employs pixel-based or subimage-based auto-regression for probability estimation, which achieves desirable performances. However, the existing works only consider context dependencies in one direction, namely, those symbols that appear before the current symbol in raster order. We believe that the dependencies between the current and future symbols should be further considered. In this work, we propose a deep lossless image compression via masked sampling and coarse-to-fine auto-regression. It combines lossy reconstruction and progressive residual compression, which fuses contexts from various directions and is more consistent with human perception. Specifically, the residuals are decomposed via T iterative masked sampling, and each sampling consists of three steps: 1) probability estimation, 2) mask computation, and 3) arithmetic coding. The iterative process progressively refines our prediction and gradually presents a real image. Extensive experimental results show that compared with the existing traditional and learned lossless compression, our method achieves comparable compression performance on extensive datasets with competitive coding speed and more flexibility.