paper-with-me

Papers

Task-driven single-image super-resolution reconstruction of document scans

2024-07-12 · Maciej Zyrek, Michal Kawulok

Super-resolution reconstruction is aimed at generating images of high spatial resolution from low-resolution observations. State-of-the-art super-resolution techniques underpinned with deep learning allow for obtaining results of outstanding visual quality, but it is seldom verified whether they constitute a valuable source for specific computer vision applications. In this paper, we investigate the possibility of employing super-resolution as a preprocessing step to improve optical character recognition from document scans. To achieve that, we propose to train deep networks for single-image super-resolution in a task-driven way to make them better adapted for the purpose of text detection. As problems limited to a specific task are heavily ill-posed, we introduce a multi-task loss function that embraces components related with text detection coupled with those guided by image similarity. The obtained results reported in this paper are encouraging and they constitute an important step towards real-world super-resolution of document images.

📄 PDF Abstract BibTeX arXiv:2407.08993

Code (0)

등록된 구현이 없습니다.

Tasks

Image Super-ResolutionOptical Character RecognitionSuper-ResolutionText Detection

Similar Papers 제목 키워드 기반

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

2025-06-08 · Maciej Zyrek, Tomasz Tarasiewicz, Jakub Sadel, Aleksandra Krzywon 외

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 d…

Image Super-ResolutionMulti-Task LearningOptical Character RecognitionSuper-Resolution+1

Feature-Driven Super-Resolution for Object Detection

2020-04-01 · Bin Wang, Tao Lu, Yanduo Zhang

Although some convolutional neural networks (CNNs) based super-resolution (SR) algorithms yield good visual performances on single images recently. Most of them focus on perfect perceptual quality but ignore specific nee…

Image ReconstructionObjectobject-detectionObject Detection+1

Toward task-driven satellite image super-resolution

2025-03-19 · Maciej Ziaja, Pawel Kowaleczko, Daniel Kostrzewa, Nicolas Longépé 외

Super-resolution is aimed at reconstructing high-resolution images from low-resolution observations. State-of-the-art approaches underpinned with deep learning allow for obtaining outstanding results, generating images o…

Image Super-Resolutionsatellite image super-resolutionSuper-Resolution

SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Models

2021-04-30 · Haoying Li, Yifan Yang, Meng Chang, Huajun Feng 외

Single image super-resolution (SISR) aims to reconstruct high-resolution (HR) images from the given low-resolution (LR) ones, which is an ill-posed problem because one LR image corresponds to multiple HR images. Recently…

Image ManipulationImage Super-ResolutionSuper-Resolution

WaveMixSR-V2: Enhancing Super-resolution with Higher Efficiency

2024-09-16 · Pranav Jeevan, Neeraj Nixon, Amit Sethi

Recent advancements in single image super-resolution have been predominantly driven by token mixers and transformer architectures. WaveMixSR utilized the WaveMix architecture, employing a two-dimensional discrete wavelet…

Image Super-ResolutionSuper-Resolution