# Task-driven real-world super-resolution of document scans

arXiv: https://arxiv.org/abs/2506.06953 · HTML: https://mlsanity.com/paper/2506.06953/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 51 references that are in the map.
- First posted on arXiv 8 Jun 2025.

## Builds on (most cited first, 26 of 26)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [Accurate Image Super-Resolution Using Very Deep Convolutional Networks](https://mlsanity.com/paper/1511.04587/) (2015)
- [GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks](https://mlsanity.com/paper/1711.02257/) (2017)
- [Residual Dense Network for Image Super-Resolution](https://mlsanity.com/paper/1802.08797/) (2018)
- [End-to-End Multi-Task Learning with Attention](https://mlsanity.com/paper/1803.10704/) (2018)
- [An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition](https://mlsanity.com/paper/1507.05717/) (2015)
- [Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Model](https://mlsanity.com/paper/1904.00523/) (2019)
- [Deep Learning for Image Super-resolution: A Survey](https://mlsanity.com/paper/1902.06068/) (2019)
- [Transformer for Single Image Super-Resolution](https://mlsanity.com/paper/2108.11084/) (2021)
- [Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filters](https://mlsanity.com/paper/1904.00889/) (2019)
- [Real-World Single Image Super-Resolution: A Brief Review](https://mlsanity.com/paper/2103.02368/) (2021)
- [Task-Driven Super Resolution: Object Detection in Low-resolution Images](https://mlsanity.com/paper/1803.11316/) (2018)
- [Extremely Lightweight Quantization Robust Real-Time Single-Image Super Resolution for Mobile Devices](https://mlsanity.com/paper/2105.10288/) (2021)
- [TextSR: Content-Aware Text Super-Resolution Guided by Recognition](https://mlsanity.com/paper/1909.07113/) (2019)
- [Swift Parameter-free Attention Network for Efficient Super-Resolution](https://mlsanity.com/paper/2311.12770/) (2023)
- [Boosting Optical Character Recognition: A Super-Resolution Approach](https://mlsanity.com/paper/1506.02211/) (2015)
- [Permutation invariance and uncertainty in multitemporal image super-resolution](https://mlsanity.com/paper/2105.12409/) (2021)
- [Large Kernel Distillation Network for Efficient Single Image Super-Resolution](https://mlsanity.com/paper/2407.14340/) (2024)
- [Facial Expression Restoration Based on Improved Graph Convolutional Networks](https://mlsanity.com/paper/1910.10344/) (2019)
- [Benefiting from Multitask Learning to Improve Single Image Super-Resolution](https://mlsanity.com/paper/1907.12488/) (2019)
- [Semantically Accurate Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/2205.08659/) (2022)
- [One-stage Low-resolution Text Recognition with High-resolution Knowledge Transfer](https://mlsanity.com/paper/2308.02770/) (2023)
- [Task-driven single-image super-resolution reconstruction of document scans](https://mlsanity.com/paper/2407.08993/) (2024)

## Abstract (arXiv)

Single-image super-resolution refers to the reconstruction of a high-resolution image from a single low-resolution observation. Although recent deep learning-based methods have demonstrated notable success on simulated datasets -- with low-resolution images obtained by degrading and downsampling high-resolution ones -- they frequently fail to generalize to real-world settings, such as document scans, which are affected by complex degradations and semantic variability. In this study, we introduce a task-driven, multi-task learning framework for training a super-resolution network specifically optimized for optical character recognition tasks. We propose to incorporate auxiliary loss functions derived from high-level vision tasks, including text detection using the connectionist text proposal network, text recognition via a convolutional recurrent neural network, keypoints localization using Key.Net, and hue consistency. To balance these diverse objectives, we employ dynamic weight averaging mechanism, which adaptively adjusts the relative importance of each loss term based on its convergence behavior. We validate our approach upon the SRResNet architecture, which is a well-established technique for single-image super-resolution. Experimental evaluations on both simulated and real-world scanned document datasets demonstrate that the proposed approach improves text detection, measured with intersection over union, while preserving overall image fidelity. These findings underscore the value of multi-objective optimization in super-resolution models for bridging the gap between simulated training regimes and practical deployment in real-world scenarios.