Deep Lossy Plus Residual Coding for Lossless and Near-lossless Image Compression
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2022
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916087001513984 |
|---|---|
| author | Bai, Yuanchao Liu, Xianming Wang, Kai Ji, Xiangyang Wu, Xiaolin Gao, Wen |
| author_facet | Bai, Yuanchao Liu, Xianming Wang, Kai Ji, Xiangyang Wu, Xiaolin Gao, Wen |
| contents | Lossless and near-lossless image compression is of paramount importance to professional users in many technical fields, such as medicine, remote sensing, precision engineering and scientific research. But despite rapidly growing research interests in learning-based image compression, no published method offers both lossless and near-lossless modes. In this paper, we propose a unified and powerful deep lossy plus residual (DLPR) coding framework for both lossless and near-lossless image compression. In the lossless mode, the DLPR coding system first performs lossy compression and then lossless coding of residuals. We solve the joint lossy and residual compression problem in the approach of VAEs, and add autoregressive context modeling of the residuals to enhance lossless compression performance. In the near-lossless mode, we quantize the original residuals to satisfy a given $\ell_\infty$ error bound, and propose a scalable near-lossless compression scheme that works for variable $\ell_\infty$ bounds instead of training multiple networks. To expedite the DLPR coding, we increase the degree of algorithm parallelization by a novel design of coding context, and accelerate the entropy coding with adaptive residual interval. Experimental results demonstrate that the DLPR coding system achieves both the state-of-the-art lossless and near-lossless image compression performance with competitive coding speed. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2209_04847 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Deep Lossy Plus Residual Coding for Lossless and Near-lossless Image Compression Bai, Yuanchao Liu, Xianming Wang, Kai Ji, Xiangyang Wu, Xiaolin Gao, Wen Image and Video Processing Computer Vision and Pattern Recognition Lossless and near-lossless image compression is of paramount importance to professional users in many technical fields, such as medicine, remote sensing, precision engineering and scientific research. But despite rapidly growing research interests in learning-based image compression, no published method offers both lossless and near-lossless modes. In this paper, we propose a unified and powerful deep lossy plus residual (DLPR) coding framework for both lossless and near-lossless image compression. In the lossless mode, the DLPR coding system first performs lossy compression and then lossless coding of residuals. We solve the joint lossy and residual compression problem in the approach of VAEs, and add autoregressive context modeling of the residuals to enhance lossless compression performance. In the near-lossless mode, we quantize the original residuals to satisfy a given $\ell_\infty$ error bound, and propose a scalable near-lossless compression scheme that works for variable $\ell_\infty$ bounds instead of training multiple networks. To expedite the DLPR coding, we increase the degree of algorithm parallelization by a novel design of coding context, and accelerate the entropy coding with adaptive residual interval. Experimental results demonstrate that the DLPR coding system achieves both the state-of-the-art lossless and near-lossless image compression performance with competitive coding speed. |
| title | Deep Lossy Plus Residual Coding for Lossless and Near-lossless Image Compression |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2209.04847 |