RDEIC: Accelerating Diffusion-Based Extreme Image Compression with Relay Residual Diffusion
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916758132097024 |
|---|---|
| author | Li, Zhiyuan Zhou, Yanhui Wei, Hao Ge, Chenyang Mian, Ajmal |
| author_facet | Li, Zhiyuan Zhou, Yanhui Wei, Hao Ge, Chenyang Mian, Ajmal |
| contents | Diffusion-based extreme image compression methods have achieved impressive performance at extremely low bitrates. However, constrained by the iterative denoising process that starts from pure noise, these methods are limited in both fidelity and efficiency. To address these two issues, we present Relay Residual Diffusion Extreme Image Compression (RDEIC), which leverages compressed feature initialization and residual diffusion. Specifically, we first use the compressed latent features of the image with added noise, instead of pure noise, as the starting point to eliminate the unnecessary initial stages of the denoising process. Second, we directly derive a novel residual diffusion equation from Stable Diffusion's original diffusion equation that reconstructs the raw image by iteratively removing the added noise and the residual between the compressed and target latent features. In this way, we effectively combine the efficiency of residual diffusion with the powerful generative capability of Stable Diffusion. Third, we propose a fixed-step fine-tuning strategy to eliminate the discrepancy between the training and inference phases, thereby further improving the reconstruction quality. Extensive experiments demonstrate that the proposed RDEIC achieves state-of-the-art visual quality and outperforms existing diffusion-based extreme image compression methods in both fidelity and efficiency. The source code and pre-trained models are available at https://github.com/huai-chang/RDEIC. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_02640 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | RDEIC: Accelerating Diffusion-Based Extreme Image Compression with Relay Residual Diffusion Li, Zhiyuan Zhou, Yanhui Wei, Hao Ge, Chenyang Mian, Ajmal Image and Video Processing Computer Vision and Pattern Recognition Diffusion-based extreme image compression methods have achieved impressive performance at extremely low bitrates. However, constrained by the iterative denoising process that starts from pure noise, these methods are limited in both fidelity and efficiency. To address these two issues, we present Relay Residual Diffusion Extreme Image Compression (RDEIC), which leverages compressed feature initialization and residual diffusion. Specifically, we first use the compressed latent features of the image with added noise, instead of pure noise, as the starting point to eliminate the unnecessary initial stages of the denoising process. Second, we directly derive a novel residual diffusion equation from Stable Diffusion's original diffusion equation that reconstructs the raw image by iteratively removing the added noise and the residual between the compressed and target latent features. In this way, we effectively combine the efficiency of residual diffusion with the powerful generative capability of Stable Diffusion. Third, we propose a fixed-step fine-tuning strategy to eliminate the discrepancy between the training and inference phases, thereby further improving the reconstruction quality. Extensive experiments demonstrate that the proposed RDEIC achieves state-of-the-art visual quality and outperforms existing diffusion-based extreme image compression methods in both fidelity and efficiency. The source code and pre-trained models are available at https://github.com/huai-chang/RDEIC. |
| title | RDEIC: Accelerating Diffusion-Based Extreme Image Compression with Relay Residual Diffusion |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.02640 |