UHD Image Deblurring via Autoregressive Flow with Ill-conditioned Constraints

2026-03-11

AI Summary

This work addresses the challenge of ultra-high-definition image deblurring, where preserving fine details and maintaining computational efficiency are often at odds. The authors propose an autoregressive flow method that progressively reconstructs sharp images through a coarse-to-fine multi-scale strategy under ill-posed constraints. A key innovation is the introduction of a condition number regularization mechanism, which suppresses ill-conditioning in feature attention matrices, thereby significantly enhancing cross-scale consistency and numerical stability. By integrating flow matching with efficient ODE solvers (Euler/Heun), the method achieves high-quality deblurring on 4K and higher-resolution images, striking an excellent balance between detail fidelity and inference efficiency.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Hardware-aware ML
• Search and Optimization: Non-convex Optimization

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

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.

Problem

• UHD image deblurring
• fine-grained detail recovery
• inference efficiency
• ill-conditioned constraints
• computational cost

Innovation

• Autoregressive Flow
• UHD Image Deblurring
• Flow Matching
• Ill-conditioned Constraint
• Coarse-to-fine Restoration