Low-Light Image and Video Enhancement Using Deep Learning: A Survey

Li, Chongyi; Guo, Chunle; Han, Ling-Hao; Jiang, Jun; Cheng, Ming–Ming; Gu, Jun; Loy, Chen Change

doi:10.48550/arxiv.2104.10729

Cited by 2 publications

(5 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Low-light Enhancement. Deep networks have become the mainstream in low-light enhancement (LLE) [15]. The first CNN model LL-Net [21] employs an autoencoder to learn denoising and light enhancement simultaneously.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

LEDNet: Joint Low-light Enhancement and Deblurring in the Dark

Zhou¹,

Li²,

Loy³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

sg https://shangchenzhou.com/projects/LEDNet (e) LEDNet (Ours) (a) Input (b) RUAS (c) RUAS → MIMO-UNet (d) MIMO-UNet Figure 1. A comparison on the real-world night blurry images shows that existing low-light enhancement and deblurring methods fail in coping with the night blurry images. (a) Input images. (b) Motion blur in the saturated area is enlarged after performing light enhancement using a contemporary method RUAS [20] (indicated by red arrows). (c) Applying a deblurring network MIMO-UNet [6] after light enhancement still fails in blur removal. (d) MIMO-UNet trained on day-time GoPro dataset fails to remove blur in the night-time images. (e) The proposed LEDNet trained with our LOL-Blur dataset yields satisfactory results through joint low-light enhancement and deblurring.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Prior methods address the two tasks independently, i.e., low-light enhancement [8,15,38] and image deblurring [4,10,14,26,32,44,47]. These methods made inde- pendent assumptions in their specific problem.…”

Section: Introductionmentioning

confidence: 99%

LEDNet: Joint Low-light Enhancement and Deblurring in the Dark

Zhou¹,

Li²,

Loy³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Data-driven Methods. In recent years, deep neural networks have paved the way for the lowlight image enhancement task [8,15,19,20,22,24,39,40,[42][43][44]46]. According to the supervision level, the data-driven based enhancement models can be roughly divided into the supervised group, the semi-supervised group, and the unsupervised group.…”

Section: Related Workmentioning

confidence: 99%

“…These methods shed light on learning-based low-light image enhancement, as they relieve the burden of sufficient pairwise data. However, the issues such as stable training, color distortion, correlation of cross-domain information still remain open and challenging [19].…”

Section: Related Workmentioning

confidence: 99%

“…Despite of the clear physical meaning, these models have a common challenge of the ill-posed image decomposition, especially when additional constraints are introduced to suppress multiple degeneration factors. On the other hand, many enhancement models resort to end-to-end convolutional neural networks (CNNs), in which various loss terms are designed to comprehensively tackle the degeneration factors [19]. These models treat the enhancement as the task of learning a pixel-wise mapping between image pairs.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Decoupled Low-light Image Enhancement

Hao¹,

Han²,

Guo³

et al. 2021

Preprint

View full text Add to dashboard Cite

The visual quality of photographs taken under imperfect lightness conditions can be degenerated by multiple factors, e.g., low lightness, imaging noise, color distortion and so on. Current low-light image enhancement models focus on the improvement of low lightness only, or simply deal with all the degeneration factors as a whole, therefore leading to a sub-optimal performance. In this paper, we propose to decouple the enhancement model into two sequential stages. The first stage focuses on improving the scene visibility based on a pixel-wise non-linear mapping. The second stage focuses on improving the appearance fidelity by suppressing the rest degeneration factors. The decoupled model facilitates the enhancement in two aspects. On the one hand, the whole low-light enhancement can be divided into two easier subtasks. The first one only aims to enhance the visibility. It also helps to bridge the large intensity gap between the low-light and normal-light images. In this way, the second subtask can be shaped as the local appearance adjustment. On the other hand, since the parameter matrix learned from the first stage is aware of the lightness distribution and the scene structure, it can be incorporated into the second stage as the complementary information. In the experiments, our model demonstrates the state-of-the-art performance in both qualitative and quantitative comparisons, compared with other low-light image enhancement models. In addition, the ablation studies also validate the effectiveness of our model in multiple aspects, such as model structure and loss function. The trained model is available at https://github.com/hanxuhfut/Decoupled-Low-light-Image-Enhancement.

show abstract

Low-Light Image and Video Enhancement Using Deep Learning: A Survey

Cited by 2 publications

References 14 publications

LEDNet: Joint Low-light Enhancement and Deblurring in the Dark

LEDNet: Joint Low-light Enhancement and Deblurring in the Dark

Decoupled Low-light Image Enhancement

Contact Info

Product

Resources

About