Fast Enhancement for Non-Uniform Illumination Images using Light-weight CNNs

Lv, Feifan; Liu, Bo; Lu, Feng

doi:10.1145/3394171.3413925

Cited by 75 publications

(71 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(2017) simulated multi-scale Retinex with a convolution neural network; Li et al (2018) proposed an improved network framework for correcting the illumination; Wang et al (2019b) designed a network to do Retinex decomposition in a progressive way; addressed this problem with the help of a down-sample image; Lv et al (2020) built a noise compression network for reflectance denoising; proposed a Retinex inspired unrolling scheme with network architecture search (NAS). However, as analyzed in (Lu & Zhang, 2020), directly treating the reflectance might not be very reasonable, and therefore the second methodology, that additionally takes illumination adjustment into consideration, has also been adopted in many studies.…”

Section: Retinex Inspired Deep Learning Methodsmentioning

confidence: 99%

Low-light Image Enhancement by Retinex Based Algorithm Unrolling and Adjustment

Liu¹,

Xie²,

Zhao³

et al. 2022

Preprint

View full text Add to dashboard Cite

Motivated by their recent advances, deep learning techniques have been widely applied to low-light image enhancement (LIE) problem. Among which, Retinex theory based ones, mostly following a decomposition-adjustment pipeline, have taken an important place due to its physical interpretation and promising performance. However, current investigations on Retinex based deep learning are still not sufficient, ignoring many useful experiences from traditional methods. Besides, the adjustment step is either performed with simple image processing techniques, or by complicated networks, both of which are unsatisfactory in practice. To address these issues, we propose a new deep learning framework for the LIE problem. The proposed framework contains a decomposition network inspired by algorithm unrolling, and adjustment networks considering both global brightness and local brightness sensitivity. By virtue of algorithm unrolling, both implicit priors learned from data and explicit priors borrowed from traditional methods can be embedded in the network, facilitate to better decomposition. Meanwhile, the consideration of global and local brightness can guide designing simple yet effective network modules for adjustment. Besides, to avoid manually parameter tuning, we also propose a self-supervised fine-tuning strategy, which can always guarantee a promising performance. Experiments on a series of typical LIE datasets demonstrated the effectiveness of the proposed method, both quantitatively and visually, as compared with existing methods.

show abstract

Section: Retinex Inspired Deep Learning Methodsmentioning

confidence: 99%

Low-light Image Enhancement by Retinex Based Algorithm Unrolling and Adjustment

Liu¹,

Xie²,

Zhao³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Yang et al [ 39 ] suggested a semi-supervised learning method for low-light image enhancement based on a deep recursive band network (DRBN). Lv et al [ 40 ] presented an end-to-end lightweight network for non-uniform illumination image enhancement that retains the advantages of the Retinex model and overcomes its limitations. Wang et al [ 41 ] proposed the Deep Lightening Network (DLN) composed of several lightening back-projection (LBP) blocks to estimate residuals between low-light and normal-light images and the residual between low and normal light images.…”

Section: Introductionmentioning

confidence: 99%

Low-Light Image Enhancement via Retinex-Style Decomposition of Denoised Deep Image Prior

Gao

Zhang

Luo

2022

Sensors

View full text Add to dashboard Cite

Low-light images are a common phenomenon when taking photos in low-light environments with inappropriate camera equipment, leading to shortcomings such as low contrast, color distortion, uneven brightness, and high loss of detail. These shortcomings are not only subjectively annoying but also affect the performance of many computer vision systems. Enhanced low-light images can be better applied to image recognition, object detection and image segmentation. This paper proposes a novel RetinexDIP method to enhance images. Noise is considered as a factor in image decomposition using deep learning generative strategies. The involvement of noise makes the image more real, weakens the coupling relationship between the three components, avoids overfitting, and improves generalization. Extensive experiments demonstrate that our method outperforms existing methods qualitatively and quantitatively.

show abstract

“…Deep learning, especially the deep convolutional neural network (CNN), provides an effective way to solve this problem. Instead of designing sophisticated priors, these approaches usually directly estimate clear images from the low-light images via deep end-to-end trainable networks [8], [9], [10], [11], [12], [13], [14], [15], [16], [17]. As stated in [18], the deep learning-based methods achieve better accuracy, robustness, and speed than conventional methods.…”

Section: Introductionmentioning

confidence: 99%

Structural Prior Guided Generative Adversarial Transformers for Low-Light Image Enhancement

Pan¹,

Wu²

2022

Preprint

View full text Add to dashboard Cite

We propose an effective Structural Prior guided Generative Adversarial Transformer (SPGAT) to solve low-light image enhancement. Our SPGAT mainly contains a generator with two discriminators and a structural prior estimator (SPE). The generator is based on a U-shaped Transformer which is used to explore non-local information for better clear image restoration. The SPE is used to explore useful structures from images to guide the generator for better structural detail estimation. To generate more realistic images, we develop a new structural prior guided adversarial learning method by building the skip connections between the generator and discriminators so that the discriminators can better discriminate between real and fake features. Finally, we propose a parallel windowsbased Swin Transformer block to aggregate different level hierarchical features for high-quality image restoration. Experimental results demonstrate that the proposed SPGAT performs favorably against recent state-of-the-art methods on both synthetic and real-world datasets.

show abstract

Fast Enhancement for Non-Uniform Illumination Images using Light-weight CNNs

Cited by 75 publications

References 26 publications

Low-light Image Enhancement by Retinex Based Algorithm Unrolling and Adjustment

Low-light Image Enhancement by Retinex Based Algorithm Unrolling and Adjustment

Low-Light Image Enhancement via Retinex-Style Decomposition of Denoised Deep Image Prior

Structural Prior Guided Generative Adversarial Transformers for Low-Light Image Enhancement

Contact Info

Product

Resources

About