Deep Lossless Image Compression via Masked Sampling and Coarse-to-Fine Auto-Regression
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915198012489728 |
|---|---|
| author | Li, Tiantian Xia, Qunbing Li, Yue Guo, Ruixiao Yang, Gaobo |
| author_facet | Li, Tiantian Xia, Qunbing Li, Yue Guo, Ruixiao Yang, Gaobo |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_11231 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Deep Lossless Image Compression via Masked Sampling and Coarse-to-Fine Auto-Regression Li, Tiantian Xia, Qunbing Li, Yue Guo, Ruixiao Yang, Gaobo Image and Video Processing Computer Vision and Pattern Recognition 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. |
| title | Deep Lossless Image Compression via Masked Sampling and Coarse-to-Fine Auto-Regression |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.11231 |