Extremely Low-light Image Enhancement with Scene Text Restoration

@article{Hsu2022ExtremelyLI,
  title={Extremely Low-light Image Enhancement with Scene Text Restoration},
  author={Po-Hao Hsu and Che-Tsung Lin and Chun Chet Ng and Jie-Long Kew and Mei Yih Tan and Shang-Hong Lai and Chee Seng Chan and Christopher Zach},
  journal={ArXiv},
  year={2022},
  volume={abs/2204.00630}
}
—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 over- all quality of the image simultaneously under extremely low-light… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 30 REFERENCES
LIME: Low-Light Image Enhancement via Illumination Map Estimation
TLDR
Experiments on a number of challenging low-light images are present to reveal the efficacy of the proposed LIME and show its superiority over several state-of-the-arts in terms of enhancement quality and efficiency.
Arbitrarily-Oriented Text Detection in Low Light Natural Scene Images
TLDR
The proposed method introduces Cloud of Line Distribution Feature (COLD), which studies the distribution of pixels of text candidates in the polar domain, and uses Maximally Stable Extremal Regions (MSER) for detecting text candidates from enhanced images.
EEMEFN: Low-Light Image Enhancement via Edge-Enhanced Multi-Exposure Fusion Network
TLDR
This paper proposes a two-stage method called Edge-Enhanced Multi-Exposure Fusion Network (EEMEFN) to enhance extremely low-light images, which can reconstruct high-quality images with sharp edges when minimizing the pixel-wise loss.
Low-light Image Enhancement Algorithm Based on Retinex and Generative Adversarial Network
TLDR
The proposed GAN-based network and employed Retinex theory have proven to be effective in dealing with the low-light image enhancement problems, which will benefit the image processing with no doubt.
Learning to See in the Dark
TLDR
A pipeline for processing low-light images is developed, based on end-to-end training of a fully-convolutional network that operates directly on raw sensor data and replaces much of the traditional image processing pipeline, which tends to perform poorly on such data.
Deep Retinex Decomposition for Low-Light Enhancement
TLDR
Extensive experiments demonstrate that the proposed deep Retinex-Net learned on this LOw-Light dataset not only achieves visually pleasing quality for low-light enhancement but also provides a good representation of image decomposition.
LLNet: A deep autoencoder approach to natural low-light image enhancement
EnlightenGAN: Deep Light Enhancement Without Paired Supervision
TLDR
This paper proposes a highly effective unsupervised generative adversarial network, dubbed EnlightenGAN, that can be trained without low/normal-light image pairs, yet proves to generalize very well on various real-world test images.
A Bio-Inspired Multi-Exposure Fusion Framework for Low-light Image Enhancement
TLDR
A dual-exposure fusion algorithm is proposed to provide an accurate contrast and lightness enhancement to solve the problem of low-light image enhancement through image fusion and weight matrix fusion.
Low-light image enhancement using CNN and bright channel prior
TLDR
A convolutional neural network (CNN) based architecture is proposed to denoise low-light images and an effective filter is designed to adaptively estimate environment light in different image areas to enhance image contrast.
...
...