Extremely Low-light Image Enhancement with Scene Text Restoration

• URL: http://arxiv.org/abs/2204.00630v1
• Date: Fri, 1 Apr 2022 16:10:14 GMT
• Title: Extremely Low-light Image Enhancement with Scene Text Restoration
• Authors: Pohao Hsu, Che-Tsung Lin, Chun Chet Ng, Jie-Long Kew, Mei Yih Tan, Shang-Hong Lai, Chee Seng Chan and Christopher Zach
• Abstract summary: A novel image enhancement framework is proposed to precisely restore the scene texts. We employ a self-regularised attention map, an edge map, and a novel text detection loss. The proposed model outperforms state-of-the-art methods in image restoration, text detection, and text spotting.
• Score: 29.08094129045479
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep learning-based methods have made impressive progress in enhancing extremely low-light images - the image quality of the reconstructed images has generally improved. However, we found out that most of these methods could not sufficiently recover the image details, for instance, the texts in the scene. In this paper, a novel image enhancement framework is proposed to precisely restore the scene texts, as well as the overall quality of the image simultaneously under extremely low-light images conditions. Mainly, we employed a self-regularised attention map, an edge map, and a novel text detection loss. In addition, leveraging synthetic low-light images is beneficial for image enhancement on the genuine ones in terms of text detection. The quantitative and qualitative experimental results have shown that the proposed model outperforms state-of-the-art methods in image restoration, text detection, and text spotting on See In the Dark and ICDAR15 datasets.

Related papers

• Text in the Dark: Extremely Low-Light Text Image Enhancement [20.631833980353704]
  Low-light text images are common in natural scenes, making scene text detection and recognition challenging. We propose a novel encoder-decoder framework with an edge-aware attention module to focus on scene text regions during enhancement. Our proposed method uses novel text detection and edge reconstruction losses to emphasize low-level scene text features, leading to successful text extraction.
  arXiv  Detail & Related papers  (2024-04-22T12:39:12Z)
• ENTED: Enhanced Neural Texture Extraction and Distribution for Reference-based Blind Face Restoration [51.205673783866146]
  We present ENTED, a new framework for blind face restoration that aims to restore high-quality and realistic portrait images. We utilize a texture extraction and distribution framework to transfer high-quality texture features between the degraded input and reference image. The StyleGAN-like architecture in our framework requires high-quality latent codes to generate realistic images.
  arXiv  Detail & Related papers  (2024-01-13T04:54:59Z)
• Improving Image Restoration through Removing Degradations in Textual Representations [60.79045963573341]
  We introduce a new perspective for improving image restoration by removing degradation in the textual representations of a degraded image. To address the cross-modal assistance, we propose to map the degraded images into textual representations for removing the degradations. In particular, We ingeniously embed an image-to-text mapper and text restoration module into CLIP-equipped text-to-image models to generate the guidance.
  arXiv  Detail & Related papers  (2023-12-28T19:18:17Z)
• Enhancing Scene Text Detectors with Realistic Text Image Synthesis Using Diffusion Models [63.99110667987318]
  We present DiffText, a pipeline that seamlessly blends foreground text with the background's intrinsic features. With fewer text instances, our produced text images consistently surpass other synthetic data in aiding text detectors.
  arXiv  Detail & Related papers  (2023-11-28T06:51:28Z)
• Deep Image Compression Using Scene Text Quality Assessment [6.445605125467574]
  A high compression rate with general methods may degrade images, resulting in unreadable texts. We develop a scene text image quality assessment model to assess text quality in compressed images.
  arXiv  Detail & Related papers  (2023-05-19T01:26:43Z)
• Semantic-Preserving Augmentation for Robust Image-Text Retrieval [27.2916415148638]
  RVSE consists of novel image-based and text-based augmentation techniques called semantic preserving augmentation for image (SPAugI) and text (SPAugT) Since SPAugI and SPAugT change the original data in a way that its semantic information is preserved, we enforce the feature extractors to generate semantic aware embedding vectors. From extensive experiments using benchmark datasets, we show that RVSE outperforms conventional retrieval schemes in terms of image-text retrieval performance.
  arXiv  Detail & Related papers  (2023-03-10T03:50:44Z)
• Diffusion in the Dark: A Diffusion Model for Low-Light Text Recognition [78.50328335703914]
  Diffusion in the Dark (DiD) is a diffusion model for low-light image reconstruction for text recognition. We demonstrate that DiD, without any task-specific optimization, can outperform SOTA low-light methods in low-light text recognition on real images.
  arXiv  Detail & Related papers  (2023-03-07T23:52:51Z)
• Re-Imagen: Retrieval-Augmented Text-to-Image Generator [58.60472701831404]
  Retrieval-Augmented Text-to-Image Generator (Re-Imagen) Retrieval-Augmented Text-to-Image Generator (Re-Imagen)
  arXiv  Detail & Related papers  (2022-09-29T00:57:28Z)
• Enhancing Low-Light Images in Real World via Cross-Image Disentanglement [58.754943762945864]
  We propose a new low-light image enhancement dataset consisting of misaligned training images with real-world corruptions. Our model achieves state-of-the-art performances on both the newly proposed dataset and other popular low-light datasets.
  arXiv  Detail & Related papers  (2022-01-10T03:12:52Z)
• Burst Denoising of Dark Images [19.85860245798819]
  We propose a deep learning framework for obtaining clean and colorful RGB images from extremely dark raw images. The backbone of our framework is a novel coarse-to-fine network architecture that generates high-quality outputs in a progressive manner. Our experiments demonstrate that the proposed approach leads to perceptually more pleasing results than state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-03-17T17:17:36Z)

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.