Dual-Representation Image Compression at Ultra-Low Bitrates via Explicit Semantics and Implicit Textures
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914306793144320 |
|---|---|
| author | Zhou, Chuqin Ling, Xiaoyue Chen, Yunuo Dai, Jincheng Lu, Guo Zhang, Wenjun |
| author_facet | Zhou, Chuqin Ling, Xiaoyue Chen, Yunuo Dai, Jincheng Lu, Guo Zhang, Wenjun |
| contents | While recent neural codecs achieve strong performance at low bitrates when optimized for perceptual quality, their effectiveness deteriorates significantly under ultra-low bitrate conditions. To mitigate this, generative compression methods leveraging semantic priors from pretrained models have emerged as a promising paradigm. However, existing approaches are fundamentally constrained by a tradeoff between semantic faithfulness and perceptual realism. Methods based on explicit representations preserve content structure but often lack fine-grained textures, whereas implicit methods can synthesize visually plausible details at the cost of semantic drift. In this work, we propose a unified framework that bridges this gap by coherently integrating explicit and implicit representations in a training-free manner. Specifically, We condition a diffusion model on explicit high-level semantics while employing reverse-channel coding to implicitly convey fine-grained details. Moreover, we introduce a plug-in encoder that enables flexible control of the distortion-perception tradeoff by modulating the implicit information. Extensive experiments demonstrate that the proposed framework achieves state-of-the-art rate-perception performance, outperforming existing methods and surpassing DiffC by 29.92%, 19.33%, and 20.89% in DISTS BD-Rate on the Kodak, DIV2K, and CLIC2020 datasets, respectively. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_05213 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Dual-Representation Image Compression at Ultra-Low Bitrates via Explicit Semantics and Implicit Textures Zhou, Chuqin Ling, Xiaoyue Chen, Yunuo Dai, Jincheng Lu, Guo Zhang, Wenjun Computer Vision and Pattern Recognition While recent neural codecs achieve strong performance at low bitrates when optimized for perceptual quality, their effectiveness deteriorates significantly under ultra-low bitrate conditions. To mitigate this, generative compression methods leveraging semantic priors from pretrained models have emerged as a promising paradigm. However, existing approaches are fundamentally constrained by a tradeoff between semantic faithfulness and perceptual realism. Methods based on explicit representations preserve content structure but often lack fine-grained textures, whereas implicit methods can synthesize visually plausible details at the cost of semantic drift. In this work, we propose a unified framework that bridges this gap by coherently integrating explicit and implicit representations in a training-free manner. Specifically, We condition a diffusion model on explicit high-level semantics while employing reverse-channel coding to implicitly convey fine-grained details. Moreover, we introduce a plug-in encoder that enables flexible control of the distortion-perception tradeoff by modulating the implicit information. Extensive experiments demonstrate that the proposed framework achieves state-of-the-art rate-perception performance, outperforming existing methods and surpassing DiffC by 29.92%, 19.33%, and 20.89% in DISTS BD-Rate on the Kodak, DIV2K, and CLIC2020 datasets, respectively. |
| title | Dual-Representation Image Compression at Ultra-Low Bitrates via Explicit Semantics and Implicit Textures |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.05213 |