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

• URL: http://arxiv.org/abs/2210.08216v1
• Date: Sat, 15 Oct 2022 07:19:23 GMT
• Title: UDoc-GAN: Unpaired Document Illumination Correction with Background Light Prior
• Authors: Yonghui Wang, Wengang Zhou, Zhenbo Lu, Houqiang Li
• Abstract summary: UDoc-GAN is first framework to address the problem of document illumination correction under the unpaired setting. We first predict the ambient light features of the document. Then, according to the characteristics of different level of ambient lights, we re-formulate the cycle consistency constraint. Compared with the state-of-the-art approaches, our method demonstrates promising performance in terms of character error rate (CER) and edit distance (ED)
• Score: 128.19212716007794
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Document images captured by mobile devices are usually degraded by uncontrollable illumination, which hampers the clarity of document content. Recently, a series of research efforts have been devoted to correcting the uneven document illumination. However, existing methods rarely consider the use of ambient light information, and usually rely on paired samples including degraded and the corrected ground-truth images which are not always accessible. To this end, we propose UDoc-GAN, the first framework to address the problem of document illumination correction under the unpaired setting. Specifically, we first predict the ambient light features of the document. Then, according to the characteristics of different level of ambient lights, we re-formulate the cycle consistency constraint to learn the underlying relationship between normal and abnormal illumination domains. To prove the effectiveness of our approach, we conduct extensive experiments on DocProj dataset under the unpaired setting. Compared with the state-of-the-art approaches, our method demonstrates promising performance in terms of character error rate (CER) and edit distance (ED), together with better qualitative results for textual detail preservation. The source code is now publicly available at https://github.com/harrytea/UDoc-GAN.

Related papers

• Towards Image Ambient Lighting Normalization [47.42834070783831]
  Ambient Lighting Normalization (ALN) enables the study of interactions between shadows, unifying image restoration and shadow removal in a broader context. For benchmarking, we select various mainstream methods and rigorously evaluate them on Ambient6K. Experiments show that IFBlend achieves SOTA scores on Ambient6K and exhibits competitive performance on conventional shadow removal benchmarks.
  arXiv  Detail & Related papers  (2024-03-27T16:20:55Z)
• Learning Real-World Image De-Weathering with Imperfect Supervision [57.748585821252824]
  Existing real-world de-weathering datasets often exhibit inconsistent illumination, position, and textures between the ground-truth images and the input degraded images. We develop a Consistent Label Constructor (CLC) to generate a pseudo-label as consistent as possible with the input degraded image. We combine the original imperfect labels and pseudo-labels to jointly supervise the de-weathering model by the proposed Information Allocation Strategy.
  arXiv  Detail & Related papers  (2023-10-23T14:02:57Z)
• Deep Unrestricted Document Image Rectification [110.61517455253308]
  We present DocTr++, a novel unified framework for document image rectification. We upgrade the original architecture by adopting a hierarchical encoder-decoder structure for multi-scale representation extraction and parsing. We contribute a real-world test set and metrics applicable for evaluating the rectification quality.
  arXiv  Detail & Related papers  (2023-04-18T08:00:54Z)
• Designing An Illumination-Aware Network for Deep Image Relighting [69.750906769976]
  We present an Illumination-Aware Network (IAN) which follows the guidance from hierarchical sampling to progressively relight a scene from a single image. In addition, an Illumination-Aware Residual Block (IARB) is designed to approximate the physical rendering process. Experimental results show that our proposed method produces better quantitative and qualitative relighting results than previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-07-21T16:21:24Z)
• DocScanner: Robust Document Image Rectification with Progressive Learning [162.03694280524084]
  This work presents DocScanner, a new deep network architecture for document image rectification. DocScanner maintains a single estimate of the rectified image, which is progressively corrected with a recurrent architecture. The iterative refinements make DocScanner converge to a robust and superior performance, and the lightweight recurrent architecture ensures the running efficiency.
  arXiv  Detail & Related papers  (2021-10-28T09:15:02Z)
• Auto White-Balance Correction for Mixed-Illuminant Scenes [52.641704254001844]
  Auto white balance (AWB) is applied by camera hardware to remove color cast caused by scene illumination. This paper presents an effective AWB method to deal with such mixed-illuminant scenes. Our method does not require illuminant estimation, as is the case in traditional camera AWB modules.
  arXiv  Detail & Related papers  (2021-09-17T20:13:31Z)
• Intrinsic Decomposition of Document Images In-the-Wild [28.677728405031782]
  We present a learning-based method that directly estimates document reflectance based on intrinsic image formation. The proposed architecture works in a self-supervised manner where only the synthetic texture is used as a weak training signal. Our reflectance estimation scheme, when used as a pre-processing step of an OCR pipeline, shows a 26% improvement of character error rate.
  arXiv  Detail & Related papers  (2020-11-29T21:39:58Z)
• Approach for Document Detection by Contours and Contrasts [0.0]
  This paper considers arbitrary document detection performed on a mobile device. We propose a modification of the contour-based method, in which the competing contour location hypotheses are ranked according to the contrast between the areas inside and outside the border. The proposed method provides unmatched state-of-the-art performance on the open MIDV-500 dataset, and it demonstrates results comparable with state-of-the-art performance on the SmartDoc dataset.
  arXiv  Detail & Related papers  (2020-08-06T12:44:40Z)
• Can You Read Me Now? Content Aware Rectification using Angle Supervision [14.095728009592763]
  We present CREASE: Content Aware Rectification using Angle Supervision, the first learned method for document rectification. Our method surpasses previous approaches in terms of OCR accuracy, geometric error and visual similarity.
  arXiv  Detail & Related papers  (2020-08-05T16:58:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.