Adaptive Identification of Blurred Regions for Accurate Image Deblurring

2025-02-28

AI Summary

Existing image deblurring methods commonly assume spatially uniform blur, neglecting the spatial heterogeneity of degradation severity, which leads to inaccurate local restoration. To address this, we propose the Adaptive Image Blur-aware Network (AIBNet), a novel framework for blur-region-aware and region-differentiated restoration. AIBNet introduces the Spatial Feature Difference Handling Block (SFDHBlock) to precisely localize blur regions; the High-Frequency Selection Block (HFSBlock) to dynamically preserve salient high-frequency details; Spatial Feature Enhancement Module (SFEM); learnable high-frequency filtering; an encoder-decoder decoupled architecture; and a progressive training strategy. Extensive experiments on multiple benchmark datasets demonstrate state-of-the-art performance, with significant improvements in local detail reconstruction fidelity and robustness to noise.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Image deblurring aims to restore high-quality images from blurred ones. While existing deblurring methods have made significant progress, most overlook the fact that the degradation degree varies across different regions. In this paper, we propose AIBNet, a network that adaptively identifies the blurred regions, enabling differential restoration of these regions. Specifically, we design a spatial feature differential handling block (SFDHBlock), with the core being the spatial domain feature enhancement module (SFEM). Through the feature difference operation, SFEM not only helps the model focus on the key information in the blurred regions but also eliminates the interference of implicit noise. Additionally, based on the fact that the difference between sharp and blurred images primarily lies in the high-frequency components, we propose a high-frequency feature selection block (HFSBlock). The HFSBlock first uses learnable filters to extract high-frequency features and then selectively retains the most important ones. To fully leverage the decoder's potential, we use a pre-trained model as the encoder and incorporate the above modules only in the decoder. Finally, to alleviate the resource burden during training, we introduce a progressive training strategy. Extensive experiments demonstrate that our AIBNet achieves superior performance in image deblurring.

Problem

• Adaptive identification of blurred image regions
• Differential restoration of varying degradation degrees
• High-frequency feature selection for image deblurring

Innovation

• Adaptive blurred region identification via AIBNet
• High-frequency feature selection using HFSBlock
• Progressive training strategy reduces resource burden