Docdiff: Document enhancement via residual diffusion models

Z Yang, B Liu, Y Xxiong, L Yi, G Wu, X Tang… - Proceedings of the 31st …, 2023 - dl.acm.org
Removing degradation from document images not only improves their visual quality and
readability, but also enhances the performance of numerous automated document analysis …

Textdiff: Mask-guided residual diffusion models for scene text image super-resolution

B Liu, Z Yang, P Wang, J Zhou, Z Liu, Z Song… - arXiv preprint arXiv …, 2023 - arxiv.org
The goal of scene text image super-resolution is to reconstruct high-resolution text-line
images from unrecognizable low-resolution inputs. The existing methods relying on the …

Three-stage binarization of color document images based on discrete wavelet transform and generative adversarial networks

RY Ju, YS Lin, Y Jin, CC Chen, CT Chien… - Knowledge-Based …, 2024 - Elsevier
The efficient extraction of text information from the background in degraded color document
images is an important challenge in the preservation of ancient manuscripts. The imperfect …

RAGDiffusion: Faithful Cloth Generation via External Knowledge Assimilation

X Tan, Y Li, W Shang, Y Wu, J Wang, X Chen… - arXiv preprint arXiv …, 2024 - arxiv.org
Standard clothing asset generation involves creating forward-facing flat-lay garment images
displayed on a clear background by extracting clothing information from diverse real-world …

CCDWT-GAN: Generative adversarial networks based on color channel using discrete wavelet transform for document image binarization

RY Ju, YS Lin, JS Chiang, CC Chen, WH Chen… - Pacific Rim International …, 2023 - Springer
To efficiently extract textual information from color degraded document images is a
significant research area. The prolonged imperfect preservation of ancient documents has …

An Efficient Transformer–CNN Network for Document Image Binarization

L Zhang, K Wang, Y Wan - Electronics, 2024 - mdpi.com
Color image binarization plays a pivotal role in image preprocessing work and significantly
impacts subsequent tasks, particularly for text recognition. This paper concentrates on …

Binarizing Documents by Leveraging both Space and Frequency

F Quattrini, V Pippi, S Cascianelli… - … Conference on Document …, 2024 - Springer
Abstract Document Image Binarization is a well-known problem in Document Analysis and
Computer Vision, although it is far from being solved. One of the main challenges of this task …

Efficient GANs for Document Image Binarization Based on DWT and Normalization

RY Ju, KS Wong, JS Chiang - arXiv preprint arXiv:2407.04231, 2024 - arxiv.org
For document image binarization task, generative adversarial networks (GANs) can
generate images where shadows and noise are effectively removed, which allow for text …