Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

computer-vision-1

Document Enhancement

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in document-enhancement-3

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

Use these libraries to find document-enhancement-3 models and implementations

ispamm/naf-dpm

3 papers 45

Datasets

DocUNet

StainDoc

Subtasks

No subtasks available.

Most implemented papers

DE-GAN: A Conditional Generative Adversarial Network for Document Enhancement

Mohamed Ali Souibgui, Yousri Kessentini•Sun Sep 06 2020

This paper proposes an effective end-to-end framework named document enhancement generative adversarial networks (DE-GAN) that uses the conditional GANs (cGANs) to restore severely degraded document images.

143

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

Paper Graph

DocDiff: Document Enhancement via Residual Diffusion Models

Zongyuan Yang, Baolin Liu, Yongping Xiong, Lan Yi, Guibin Wu, Ziqi Liu, Junjie Zhou, Xing Zhang•Fri May 05 2023

DocDiff is the first diffusion-based framework specifically designed for diverse challenging document enhancement problems, including document deblurring, denoising, and removal of watermarks and seals, and achieves state-of-the-art SOTA performance on multiple benchmark datasets, and can significantly enhance the readability and recognizability of degraded document images.

56 0

Paper Graph

NAF-DPM: A Nonlinear Activation-Free Diffusion Probabilistic Model for Document Enhancement

D. Comminiello, Giordano Cicchetti•Sun Apr 07 2024

NAF-DPM is proposed, a novel generative framework based on a diffusion probabilistic model (DPM) designed to restore the original quality of degraded documents and demonstrates a notable character error reduction made by OCR systems when transcribing real-world document images enhanced by the framework.

9 0

Paper Graph

Document Enhancement Using Visibility Detection

A. Tal, Netanel Kligler, S. Katz•Thu May 31 2018

This paper re-visits classical problems in document enhancement. Rather than proposing a new algorithm for a specific problem, we introduce a novel general approach. The key idea is to modify any state-of-the-art algorithm, by providing it with new information (input), improving its own results. Interestingly, this information is based on a solution to a seemingly unrelated problem of visibility detection in R3. We show that a simple representation of an image as a 3D point cloud, gives visibility detection on this cloud a new interpretation. What does it mean for a point to be visible? Although this question has been widely studied within computer vision, it has always been assumed that the point set is a sampling of a real scene. We show that the answer to this question in our context reveals unique and useful information about the image. We demonstrate the benefit of this idea for document binarization and for unshadowing.

70 0

Paper Graph

Light-weight Document Image Cleanup using Perceptual Loss

Soumyadeep Dey, Pratik Jawanpuria•Tue May 18 2021

This work proposes a light-weight encoder decoder based convolutional neural network architecture for removing the noisy elements from document images and incorporates the perceptual loss for knowledge transfer from pre-trained deep CNN network in its loss function.

11 0

Paper Graph

LP-IOANet: Efficient High Resolution Document Shadow Removal

M. K. Yucel, A. Drosou, Konstantinos Georgiadis, Evangelos Skartados, Valia Dimaridou, Albert Saà-Garriga, Bruno Manganelli•Tue Mar 21 2023

This work proposes Laplacian Pyramid with Input/Output Attention Network (LP-IOANet), a novel pipeline with a lightweight architecture and an upsampling module that outperform the state-of-the-art by a 35% relative improvement in mean average error (MAE), while running real-time in four times the resolution on a mobile device.

10 0

Paper Graph

High-Fidelity Document Stain Removal via A Large-Scale Real-World Dataset and A Memory-Augmented Transformer

Mingxian Li, Hao Sun, Yingtie Lei, Xiaofeng Zhang, Yihang Dong, Yilin Zhou, Zimeng Li, Xuhang Chen•Tue Oct 29 2024

StainDoc is constructed, the first large-scale, high-resolution dataset specifically designed for document stain removal, and StainRestorer, a Transformer-based document stain removal approach, is proposed, demonstrating superior performance over state-of-the-art methods on the Stain-Doc dataset and its variants StainDoc.Mark and Stain-Doc.Seal.

33 0

Paper Graph

Adding a benchmark result helps the community track progress.

Document Enhancement | State-of-the-Art