CharDiff: A Diffusion Model with Character-Level Guidance for License Plate Image Restoration

2025-10-20

AI Summary

This work addresses the challenging problem of restoring and recognizing severely degraded license plate images in real-world scenarios. We propose CharDiff, a character-level guided diffusion model that leverages character-wise priors extracted via an external segmentation module and a dedicated OCR component designed for low-quality images. To precisely localize and enhance character regions, CharDiff introduces CHARM—a regionalized attention mechanism conditioned on character-area masks—effectively suppressing inter-region interference. On the Roboflow-LP benchmark, CharDiff achieves a 28% relative reduction in character error rate (CER) over the strongest baseline, significantly improving both restoration fidelity and OCR accuracy. To our knowledge, this is the first work to explicitly integrate character-level semantic priors into a diffusion model framework, establishing a novel paradigm for high-fidelity reconstruction of degraded license plates and enabling robust downstream applications such as forensic analysis and intelligent transportation systems.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Large Multimodal Models (LMMs)
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

The significance of license plate image restoration goes beyond the preprocessing stage of License Plate Recognition (LPR) systems, as it also serves various purposes, including increasing evidential value, enhancing the clarity of visual interface, and facilitating further utilization of license plate images. We propose a novel diffusion-based framework with character-level guidance, CharDiff, which effectively restores and recognizes severely degraded license plate images captured under realistic conditions. CharDiff leverages fine-grained character-level priors extracted through external segmentation and Optical Character Recognition (OCR) modules tailored for low-quality license plate images. For precise and focused guidance, CharDiff incorporates a novel Character-guided Attention through Region-wise Masking (CHARM) module, which ensures that each character's guidance is restricted to its own region, thereby avoiding interference with other regions. In experiments, CharDiff significantly outperformed the baseline restoration models in both restoration quality and recognition accuracy, achieving a 28% relative reduction in CER on the Roboflow-LP dataset, compared to the best-performing baseline model. These results indicate that the structured character-guided conditioning effectively enhances the robustness of diffusion-based license plate restoration and recognition in practical deployment scenarios.

Problem

• Restores severely degraded license plate images
• Improves recognition accuracy using character-level guidance
• Enhances robustness for practical deployment scenarios

Innovation

• Diffusion model with character-level guidance restoration
• Character-guided attention with region-wise masking
• External segmentation and OCR modules for priors