Idempotence and Perceptual Image Compression
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909470373707776 |
|---|---|
| author | Xu, Tongda Zhu, Ziran He, Dailan Li, Yanghao Guo, Lina Wang, Yuanyuan Wang, Zhe Qin, Hongwei Wang, Yan Liu, Jingjing Zhang, Ya-Qin |
| author_facet | Xu, Tongda Zhu, Ziran He, Dailan Li, Yanghao Guo, Lina Wang, Yuanyuan Wang, Zhe Qin, Hongwei Wang, Yan Liu, Jingjing Zhang, Ya-Qin |
| contents | Idempotence is the stability of image codec to re-compression. At the first glance, it is unrelated to perceptual image compression. However, we find that theoretically: 1) Conditional generative model-based perceptual codec satisfies idempotence; 2) Unconditional generative model with idempotence constraint is equivalent to conditional generative codec. Based on this newfound equivalence, we propose a new paradigm of perceptual image codec by inverting unconditional generative model with idempotence constraints. Our codec is theoretically equivalent to conditional generative codec, and it does not require training new models. Instead, it only requires a pre-trained mean-square-error codec and unconditional generative model. Empirically, we show that our proposed approach outperforms state-of-the-art methods such as HiFiC and ILLM, in terms of Fréchet Inception Distance (FID). The source code is provided in https://github.com/tongdaxu/Idempotence-and-Perceptual-Image-Compression. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_08920 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Idempotence and Perceptual Image Compression Xu, Tongda Zhu, Ziran He, Dailan Li, Yanghao Guo, Lina Wang, Yuanyuan Wang, Zhe Qin, Hongwei Wang, Yan Liu, Jingjing Zhang, Ya-Qin Image and Video Processing Computer Vision and Pattern Recognition Idempotence is the stability of image codec to re-compression. At the first glance, it is unrelated to perceptual image compression. However, we find that theoretically: 1) Conditional generative model-based perceptual codec satisfies idempotence; 2) Unconditional generative model with idempotence constraint is equivalent to conditional generative codec. Based on this newfound equivalence, we propose a new paradigm of perceptual image codec by inverting unconditional generative model with idempotence constraints. Our codec is theoretically equivalent to conditional generative codec, and it does not require training new models. Instead, it only requires a pre-trained mean-square-error codec and unconditional generative model. Empirically, we show that our proposed approach outperforms state-of-the-art methods such as HiFiC and ILLM, in terms of Fréchet Inception Distance (FID). The source code is provided in https://github.com/tongdaxu/Idempotence-and-Perceptual-Image-Compression. |
| title | Idempotence and Perceptual Image Compression |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2401.08920 |