Deep Lossless Image Compression via Masked Sampling and Coarse-to-Fine Auto-Regression
This work addresses the problem of improving compression efficiency for image storage and transmission, but it is incremental as it builds on existing auto-regressive methods.
The paper tackles lossless image compression by proposing a method that considers dependencies between current and future symbols, combining lossy reconstruction and progressive residual compression. It achieves comparable compression performance on extensive datasets with competitive coding speed and flexibility.
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.