OmniScaleSR: Unleashing Scale-Controlled Diffusion Prior for Faithful and Realistic Arbitrary-Scale Image Super-Resolution
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912749062193152 |
|---|---|
| author | Chai, Xinning Cheng, Zhengxue Zhang, Yuhong Zhang, Hengsheng Qin, Yingsheng Yang, Yucai Xie, Rong Song, Li |
| author_facet | Chai, Xinning Cheng, Zhengxue Zhang, Yuhong Zhang, Hengsheng Qin, Yingsheng Yang, Yucai Xie, Rong Song, Li |
| contents | Arbitrary-scale super-resolution (ASSR) overcomes the limitation of traditional super-resolution (SR) methods that operate only at fixed scales (e.g., 4x), enabling a single model to handle arbitrary magnification. Most existing ASSR approaches rely on implicit neural representation (INR), but its regression-driven feature extraction and aggregation intrinsically limit the ability to synthesize fine details, leading to low realism. Recent diffusion-based realistic image super-resolution (Real-ISR) models leverage powerful pre-trained diffusion priors and show impressive results at the 4x setting. We observe that they can also achieve ASSR because the diffusion prior implicitly adapts to scale by encouraging high-realism generation. However, without explicit scale control, the diffusion process cannot be properly adjusted for different magnification levels, resulting in excessive hallucination or blurry outputs, especially under ultra-high scales. To address these issues, we propose OmniScaleSR, a diffusion-based realistic arbitrary-scale SR framework designed to achieve both high fidelity and high realism. We introduce explicit, diffusion-native scale control mechanisms that work synergistically with implicit scale adaptation, enabling scale-aware and content-aware modulation of the diffusion process. In addition, we incorporate multi-domain fidelity enhancement designs to further improve reconstruction accuracy. Extensive experiments on bicubic degradation benchmarks and real-world datasets show that OmniScaleSR surpasses state-of-the-art methods in both fidelity and perceptual realism, with particularly strong performance at large magnification factors. Code will be released at https://github.com/chaixinning/OmniScaleSR. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_04699 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | OmniScaleSR: Unleashing Scale-Controlled Diffusion Prior for Faithful and Realistic Arbitrary-Scale Image Super-Resolution Chai, Xinning Cheng, Zhengxue Zhang, Yuhong Zhang, Hengsheng Qin, Yingsheng Yang, Yucai Xie, Rong Song, Li Computer Vision and Pattern Recognition Arbitrary-scale super-resolution (ASSR) overcomes the limitation of traditional super-resolution (SR) methods that operate only at fixed scales (e.g., 4x), enabling a single model to handle arbitrary magnification. Most existing ASSR approaches rely on implicit neural representation (INR), but its regression-driven feature extraction and aggregation intrinsically limit the ability to synthesize fine details, leading to low realism. Recent diffusion-based realistic image super-resolution (Real-ISR) models leverage powerful pre-trained diffusion priors and show impressive results at the 4x setting. We observe that they can also achieve ASSR because the diffusion prior implicitly adapts to scale by encouraging high-realism generation. However, without explicit scale control, the diffusion process cannot be properly adjusted for different magnification levels, resulting in excessive hallucination or blurry outputs, especially under ultra-high scales. To address these issues, we propose OmniScaleSR, a diffusion-based realistic arbitrary-scale SR framework designed to achieve both high fidelity and high realism. We introduce explicit, diffusion-native scale control mechanisms that work synergistically with implicit scale adaptation, enabling scale-aware and content-aware modulation of the diffusion process. In addition, we incorporate multi-domain fidelity enhancement designs to further improve reconstruction accuracy. Extensive experiments on bicubic degradation benchmarks and real-world datasets show that OmniScaleSR surpasses state-of-the-art methods in both fidelity and perceptual realism, with particularly strong performance at large magnification factors. Code will be released at https://github.com/chaixinning/OmniScaleSR. |
| title | OmniScaleSR: Unleashing Scale-Controlled Diffusion Prior for Faithful and Realistic Arbitrary-Scale Image Super-Resolution |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.04699 |