UDoc-GAN: Unpaired Document Illumination Correction with Background Light Prior

Wang, Yonghui; Zhou, Wengang; Lu, Zhenbo; Li, Houqiang

doi:10.1145/3503161.3547916

Cited by 6 publications

(2 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3) Uneven illumination: For the characteristics of light inhomogeneity in the environment, it is possible to use the light correction network framework, UDoc-GAN, to solve it.The main thing is to convert uncertain normal to abnormal image panning to deterministic image panning with different levels of ambient light for learning guidance.In contrast, Aleth-NeRF cannot handle non-uniform illumination or shadow images.Meanwhile, UDoc-GAN algorithm is more computationally efficient in the inference stage and closer to realistic requirements [190].…”

Section: A Global Illuminationmentioning

confidence: 99%

Enhancing image resolution of confocal fluorescence microscopy with deep learning

Huang

Yao

et al. 2023

PhotoniX

View full text Add to dashboard Cite

Super-resolution optical imaging is crucial to the study of cellular processes. Current super-resolution fluorescence microscopy is restricted by the need of special fluorophores or sophisticated optical systems, or long acquisition and computational times. In this work, we present a deep-learning-based super-resolution technique of confocal microscopy. We devise a two-channel attention network (TCAN), which takes advantage of both spatial representations and frequency contents to learn a more precise mapping from low-resolution images to high-resolution ones. This scheme is robust against changes in the pixel size and the imaging setup, enabling the optimal model to generalize to different fluorescence microscopy modalities unseen in the training set. Our algorithm is validated on diverse biological structures and dual-color confocal images of actin-microtubules, improving the resolution from ~ 230 nm to ~ 110 nm. Last but not least, we demonstrate live-cell super-resolution imaging by revealing the detailed structures and dynamic instability of microtubules.

show abstract

Section: A Global Illuminationmentioning

confidence: 99%

Enhancing image resolution of confocal fluorescence microscopy with deep learning

Huang

Yao

et al. 2023

PhotoniX

View full text Add to dashboard Cite

show abstract

“…By constraining low-frequency content, optimizing the content of training data, and using model-averaging techniques, the quality of image restoration is improved. Wang et al [23] proposed the UDoc-GAN framework to solve the problem of uncontrolled lighting affecting document images captured on mobile devices. UDoc-GAN performs document light correction in nonpaired settings, learning the relationship between normal and abnormal lighting domains by predicting environmental light features and redefining cycle consistency constraints.…”

Section: Cycle Consistency Lossmentioning

confidence: 99%

Removal of Color-Document Image Show-Through Based on Self-Supervised Learning

Ni,

Liang,

2024

Applied Sciences

View full text Add to dashboard Cite

Show-through phenomena have always been a challenging issue in color-document image processing, which is widely used in various fields such as finance, education, and administration. Existing methods for processing color-document images face challenges, including dealing with double-sided documents with show-through effects, accurately distinguishing between foreground and show-through parts, and addressing the issue of insufficient real image data for supervised training. To overcome these challenges, this paper proposes a self-supervised-learning-based method for removing show-through effects in color-document images. The proposed method utilizes a two-stage-structured show-through-removal network that incorporates a double-cycle consistency loss and a pseudo-similarity loss to effectively constrain the process of show-through removal. Moreover, we constructed two datasets consisting of different show-through mixing ratios and conducted extensive experiments to verify the effectiveness of the proposed method. Experimental results demonstrate that the proposed method achieves competitive performance compared to state-of-the-art methods and can effectively perform show-through removal without the need for paired datasets. Specifically, the proposed method achieves an average PSNR of 33.85 dB on our datasets, outperforming comparable methods by a margin of 0.89 dB.

show abstract

Inv3D: a high-resolution 3D invoice dataset for template-guided single-image document unwarping

Hertlein

Naumann

Philipp

2023

IJDAR

View full text Add to dashboard Cite

Numerous business workflows involve printed forms, such as invoices or receipts, which are often manually digitalized to persistently search or store the data. As hardware scanners are costly and inflexible, smartphones are increasingly used for digitalization. Here, processing algorithms need to deal with prevailing environmental factors, such as shadows or crumples. Current state-of-the-art approaches learn supervised image dewarping models based on pairs of raw images and rectification meshes. The available results show promising predictive accuracies for dewarping, but generated errors still lead to sub-optimal information retrieval. In this paper, we explore the potential of improving dewarping models using additional, structured information in the form of invoice templates. We provide two core contributions: (1) a novel dataset, referred to as Inv3D, comprising synthetic and real-world high-resolution invoice images with structural templates, rectification meshes, and a multiplicity of per-pixel supervision signals and (2) a novel image dewarping algorithm, which extends the state-of-the-art approach GeoTr to leverage structural templates using attention. Our extensive evaluation includes an implementation of DewarpNet and shows that exploiting structured templates can improve the performance for image dewarping. We report superior performance for the proposed algorithm on our new benchmark for all metrics, including an improved local distortion of 26.1 %. We made our new dataset and all code publicly available at https://felixhertlein.github.io/inv3d.

show abstract

UDoc-GAN: Unpaired Document Illumination Correction with Background Light Prior

Abstract: Figure 1: Qualitative results of our proposed UDoc-GAN. The top row shows the geometric correction results of DocTr [8]. The second row presents the illumination correction results of our approach.

Cited by 6 publications

References 35 publications

Enhancing image resolution of confocal fluorescence microscopy with deep learning

Enhancing image resolution of confocal fluorescence microscopy with deep learning

Removal of Color-Document Image Show-Through Based on Self-Supervised Learning

Inv3D: a high-resolution 3D invoice dataset for template-guided single-image document unwarping

Contact Info

Product

Resources

About