An Adaptive Edge-Guided Dual-Network Framework for Fast QR Code Motion Deblurring

2025-10-13

AI Summary

Existing QR code motion deblurring methods neglect the strong structural regularity and sharp edge priors inherent to QR codes, resulting in low decoding success rates. To address this, we propose an adaptive edge-guided dual-network framework: (1) an Edge-Guided Attention Block (EGAB) explicitly encodes QR code edge structure priors; (2) a lightweight network (LENet) and a robust recovery network are jointly designed, with dynamic switching guided by estimated blur severity; and (3) a Transformer-based backbone enhances long-range dependency modeling. Our method achieves state-of-the-art deblurring performance on both severely and mildly blurred QR codes, boosting decoding success by +12.7% while maintaining real-time inference at 28 FPS—suitable for mobile deployment. The core contribution lies in deeply embedding structural priors into a dynamic network architecture, enabling joint optimization of accuracy, robustness, and efficiency.

Technology Category

• Computer Vision: Motion & Tracking
• Machine Learning: Learning on the Edge & Model Compression
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Algorithmic accountability and transparency on the web

Abstract

Unlike general image deblurring that prioritizes perceptual quality, QR code deblurring focuses on ensuring successful decoding. QR codes are characterized by highly structured patterns with sharp edges, a robust prior for restoration. Yet existing deep learning methods rarely exploit these priors explicitly. To address this gap, we propose the Edge-Guided Attention Block (EGAB), which embeds explicit edge priors into a Transformer architecture. Based on EGAB, we develop Edge-Guided Restormer (EG-Restormer), an effective network that significantly boosts the decoding rate of severely blurred QR codes. For mildly blurred inputs, we design the Lightweight and Efficient Network (LENet) for fast deblurring. We further integrate these two networks into an Adaptive Dual-network (ADNet), which dynamically selects the suitable network based on input blur severity, making it ideal for resource-constrained mobile devices. Extensive experiments show that our EG-Restormer and ADNet achieve state-of-the-art performance with a competitive speed. Project page: https://github.com/leejianping/ADNet

Problem

• Restoring severely blurred QR codes for successful decoding
• Exploiting structured edge priors in deep learning methods
• Adaptive network selection for mobile device efficiency

Innovation

• EGAB embeds edge priors into Transformer architecture
• EG-Restormer boosts decoding rate for severe blur
• ADNet adaptively selects networks based on blur severity