# CNN for License Plate Motion Deblurring

arXiv: https://arxiv.org/abs/1602.07873 · HTML: https://mlsanity.com/paper/1602.07873/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Feb 2016.

## Built on by (most cited first, 8 of 8)

- [Joint Face Image Restoration and Frontalization for Recognition](https://mlsanity.com/paper/2105.09907/) (2021)
- [Combining Attention Module and Pixel Shuffle for License Plate Super-Resolution](https://mlsanity.com/paper/2210.16836/) (2022)
- [Super-Resolution of License Plate Images Using Attention Modules and Sub-Pixel Convolution Layers](https://mlsanity.com/paper/2305.17313/) (2023)
- [Real-time Bangla License Plate Recognition System for Low Resource Video-based Applications](https://mlsanity.com/paper/2108.08339/) (2021)
- [MF-LPR2: Multi-Frame License Plate Image Restoration and Recognition using Optical Flow](https://mlsanity.com/paper/2508.14797/) (2025)
- [Synthesizing Annotated Image and Video Data Using a Rendering-Based Pipeline for Improved License Plate Recognition](https://mlsanity.com/paper/2209.14448/) (2022)
- [Spatially-Attentive Patch-Hierarchical Network with Adaptive Sampling for Motion Deblurring](https://mlsanity.com/paper/2402.06117/) (2024)
- [Sharing the Learned Knowledge-base to Estimate Convolutional Filter Parameters for Continual Image Restoration](https://mlsanity.com/paper/2511.05421/) (2025)

## Abstract (arXiv)

In this work we explore the previously proposed approach of direct blind deconvolution and denoising with convolutional neural networks in a situation where the blur kernels are partially constrained. We focus on blurred images from a real-life traffic surveillance system, on which we, for the first time, demonstrate that neural networks trained on artificial data provide superior reconstruction quality on real images compared to traditional blind deconvolution methods. The training data is easy to obtain by blurring sharp photos from a target system with a very rough approximation of the expected blur kernels, thereby allowing custom CNNs to be trained for a specific application (image content and blur range). Additionally, we evaluate the behavior and limits of the CNNs with respect to blur direction range and length.