mlsanityData to 7 Oct 2026

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

arXiv 2510.17330 ↗First posted 20 Oct 2025cs.CV cs.AIcited by 0

On the map: Diffusion models → Inverse problems and image restoration

Abstract (arXiv)

License plate image restoration is important not only as a preprocessing step for license plate recognition but also for enhancing evidential value, improving visual clarity, and enabling broader reuse of license plate images. We propose a novel diffusion-based framework with character-level guidance, CharDiff-LP, which effectively restores and recognizes severely degraded license plate images captured under realistic conditions. CharDiff-LP 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-LP 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-LP significantly outperformed baseline restoration models in both restoration quality and recognition accuracy, achieving a 28.3% relative reduction in character error rate (CER) on the Roboflow-LP dataset compared with the best-performing baseline.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models. Builds on 21 of its 43 references that are in the map. First posted on arXiv 20 Oct 2025.

Builds on

21 of 43 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023Recognition-Guided Diffusion Model for Scene Text Image Super-Resolution22 Nov
  2. 2023Scene Text Image Super-resolution based on Text-conditional Diffusion Models16 Nov
  3. 2021SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Models30 Apr

Other references · 18

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,618
  4. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
  5. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,218
  6. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 961
  7. 2018Residual Dense Network for Image Super-Resolutioncited by 796
  8. 2020Learning Texture Transformer Network for Image Super-Resolutioncited by 346
  9. 2019Character Region Awareness for Text Detectioncited by 273
  10. 2020Scene Text Image Super-Resolution in the Wildcited by 62
  11. 2021Text Prior Guided Scene Text Image Super-resolutioncited by 37
  12. 2022Multi-Granularity Prediction for Scene Text Recognitioncited by 36
6 more
  1. 2019An Efficient and Layout-Independent Automatic License Plate Recognition System Based on the YOLO detectorcited by 35
  2. 2022A Text Attention Network for Spatial Deformation Robust Scene Text Image Super-resolutioncited by 35
  3. 2023Super-Resolution of License Plate Images Using Attention Modules and Sub-Pixel Convolution Layerscited by 9
  4. 2022Forensic License Plate Recognition with Compression-Informed Transformerscited by 8
  5. 2024Enhancing License Plate Super-Resolution: A Layout-Aware and Character-Driven Approachcited by 8
  6. 2025MF-LPR2: Multi-Frame License Plate Image Restoration and Recognition using Optical Flowcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026LP-LLM: End-to-End Real-World Degraded License Plate Text Recognition via Large Multimodal Models
  2. 2023License Plate Super-Resolution Using Diffusion Models
  3. 2025License Plate Images Generation with Diffusion Models
  4. 2024Advancing Vehicle Plate Recognition: Multitasking Visual Language Models with VehiclePaliGemma
  5. 2026Neural Sentinel: Unified Vision Language Model (VLM) for License Plate Recognition with Human-in-the-Loop Continual Learning
  6. 2026BLPR: Robust License Plate Recognition under Viewpoint and Illumination Variations via Confidence-Driven VLM Fallback
  7. 2023DocDiff: Document Enhancement via Residual Diffusion Models
  8. 2023AutoDIR: Automatic All-in-One Image Restoration with Latent Diffusion