Ultra Lowrate Image Compression with Semantic Residual Coding and Compression-aware Diffusion
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909608684027904 |
|---|---|
| author | Ke, Anle Zhang, Xu Chen, Tong Lu, Ming Zhou, Chao Gu, Jiawen Ma, Zhan |
| author_facet | Ke, Anle Zhang, Xu Chen, Tong Lu, Ming Zhou, Chao Gu, Jiawen Ma, Zhan |
| contents | Existing multimodal large model-based image compression frameworks often rely on a fragmented integration of semantic retrieval, latent compression, and generative models, resulting in suboptimal performance in both reconstruction fidelity and coding efficiency. To address these challenges, we propose a residual-guided ultra lowrate image compression named ResULIC, which incorporates residual signals into both semantic retrieval and the diffusion-based generation process. Specifically, we introduce Semantic Residual Coding (SRC) to capture the semantic disparity between the original image and its compressed latent representation. A perceptual fidelity optimizer is further applied for superior reconstruction quality. Additionally, we present the Compression-aware Diffusion Model (CDM), which establishes an optimal alignment between bitrates and diffusion time steps, improving compression-reconstruction synergy. Extensive experiments demonstrate the effectiveness of ResULIC, achieving superior objective and subjective performance compared to state-of-the-art diffusion-based methods with - 80.7%, -66.3% BD-rate saving in terms of LPIPS and FID. Project page is available at https: //njuvision.github.io/ResULIC/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_08281 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Ultra Lowrate Image Compression with Semantic Residual Coding and Compression-aware Diffusion Ke, Anle Zhang, Xu Chen, Tong Lu, Ming Zhou, Chao Gu, Jiawen Ma, Zhan Computer Vision and Pattern Recognition Image and Video Processing Existing multimodal large model-based image compression frameworks often rely on a fragmented integration of semantic retrieval, latent compression, and generative models, resulting in suboptimal performance in both reconstruction fidelity and coding efficiency. To address these challenges, we propose a residual-guided ultra lowrate image compression named ResULIC, which incorporates residual signals into both semantic retrieval and the diffusion-based generation process. Specifically, we introduce Semantic Residual Coding (SRC) to capture the semantic disparity between the original image and its compressed latent representation. A perceptual fidelity optimizer is further applied for superior reconstruction quality. Additionally, we present the Compression-aware Diffusion Model (CDM), which establishes an optimal alignment between bitrates and diffusion time steps, improving compression-reconstruction synergy. Extensive experiments demonstrate the effectiveness of ResULIC, achieving superior objective and subjective performance compared to state-of-the-art diffusion-based methods with - 80.7%, -66.3% BD-rate saving in terms of LPIPS and FID. Project page is available at https: //njuvision.github.io/ResULIC/. |
| title | Ultra Lowrate Image Compression with Semantic Residual Coding and Compression-aware Diffusion |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2505.08281 |