UHD Image Deblurring via Autoregressive Flow with Ill-conditioned Constraints
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911505716346880 |
|---|---|
| author | Xin, Yucheng Zhao, Dawei Chen, Xiang Wu, Chen Wang, Pu Lu, Dianjie Zhang, Guijuan Jia, Xiuyi Zheng, Zhuoran |
| author_facet | Xin, Yucheng Zhao, Dawei Chen, Xiang Wu, Chen Wang, Pu Lu, Dianjie Zhang, Guijuan Jia, Xiuyi Zheng, Zhuoran |
| contents | Ultra-high-definition (UHD) image deblurring poses significant challenges for UHD restoration methods, which must balance fine-grained detail recovery and practical inference efficiency. Although prominent discriminative and generative methods have achieved remarkable results, a trade-off persists between computational cost and the ability to generate fine-grained detail for UHD image deblurring tasks. To further alleviate these issues, we propose a novel autoregressive flow method for UHD image deblurring with an ill-conditioned constraint. Our core idea is to decompose UHD restoration into a progressive, coarse-to-fine process: at each scale, the sharp estimate is formed by upsampling the previous-scale result and adding a current-scale residual, enabling stable, stage-wise refinement from low to high resolution. We further introduce Flow Matching to model residual generation as a conditional vector field and perform few-step ODE sampling with efficient Euler/Heun solvers, enriching details while keeping inference affordable. Since multi-step generation at UHD can be numerically unstable, we propose an ill-conditioning suppression scheme by imposing condition-number regularization on a feature-induced attention matrix, improving convergence and cross-scale consistency. Our method demonstrates promising performance on blurred images at 4K (3840$\times$2160) or higher resolutions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_10517 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | UHD Image Deblurring via Autoregressive Flow with Ill-conditioned Constraints Xin, Yucheng Zhao, Dawei Chen, Xiang Wu, Chen Wang, Pu Lu, Dianjie Zhang, Guijuan Jia, Xiuyi Zheng, Zhuoran Computer Vision and Pattern Recognition Ultra-high-definition (UHD) image deblurring poses significant challenges for UHD restoration methods, which must balance fine-grained detail recovery and practical inference efficiency. Although prominent discriminative and generative methods have achieved remarkable results, a trade-off persists between computational cost and the ability to generate fine-grained detail for UHD image deblurring tasks. To further alleviate these issues, we propose a novel autoregressive flow method for UHD image deblurring with an ill-conditioned constraint. Our core idea is to decompose UHD restoration into a progressive, coarse-to-fine process: at each scale, the sharp estimate is formed by upsampling the previous-scale result and adding a current-scale residual, enabling stable, stage-wise refinement from low to high resolution. We further introduce Flow Matching to model residual generation as a conditional vector field and perform few-step ODE sampling with efficient Euler/Heun solvers, enriching details while keeping inference affordable. Since multi-step generation at UHD can be numerically unstable, we propose an ill-conditioning suppression scheme by imposing condition-number regularization on a feature-induced attention matrix, improving convergence and cross-scale consistency. Our method demonstrates promising performance on blurred images at 4K (3840$\times$2160) or higher resolutions. |
| title | UHD Image Deblurring via Autoregressive Flow with Ill-conditioned Constraints |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.10517 |