Low-Light Image Enhancement via a Deep Hybrid Network

By Wenqi Ren, Sifei Liu, Lin Ma, Qianqian Xu, Xiangyu Xu, Xiaochun Cao, Junping Du, Ming-Hsuan Yang. IEEE Transactions on Image Processing, 2019

460 citations recorded by the source corpus.

Camera sensors often fail to capture clear images or videos in a poorly lit environment. In this paper, we propose a trainable hybrid network to enhance the visibility of such degraded images. The proposed network consists of two distinct streams to simultaneously learn the global content and the salient structures of the clear image in a unified network. More specifically, the content stream estimates the global content of the low-light input through an encoder–decoder network. However, the encoder in the content stream tends to lose some structure details. To remedy this, we propose a novel spatially variant recurrent neural network (RNN) as an edge stream to model edge details, with the guidance of another auto-encoder. The experimental results show that the proposed network favorably performs against the state-of-the-art low-light image enhancement algorithms.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/7f5526084cc83076f9d50e13b20c85cd2f2b2554

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation (2021, background): “[27] proposed a deep hybrid network for low-light image enhancement, which consists of two streams to learn the global content and the salient structures in a unified network.”
Learning Enriched Features for Fast Image Restoration and Enhancement (2022, unknown): “encoder-decoder networks [87], [88], [89], [90], [91], and”
Low-Light Image Enhancement With Semi-Decoupled Decomposition (2020, methodology): “For example, Ren et al. [23] design a hybrid model, in which a Recurrent Neural Network (RNN) is used to model high-frequency edges, while an auto-encoder is used to model low-frequency image contents.”
Learning Enriched Features for Real Image Restoration and Enhancement (2020, methodology): “Notable works employ Retinex-inspired networks [89,107,124], encoder-decoder networks [18,68,81], and GANs [19,51,25].”
Attention Guided Low-Light Image Enhancement with a Large Scale Low-Light Simulation Dataset (2019, background): “[59] propose a novel hybrid network contains a content stream and a salient edge stream for low-light image enhancement.”
From Fidelity to Perceptual Quality: A Semi-Supervised Approach for Low-Light Image Enhancement (2020, methodology): “Later on, various methods based on different network designs [26, 3, 24, 27, 30] are proposed.”
Low-Light Image Enhancement with Normalizing Flow (2021, methodology): “Multi-scale features are adopted (Shen et al. 2017; Tao et al. 2017; Lv et al. 2018; Ren et al. 2019) to obtain better visual quality.”
Human-Aware Motion Deblurring (2019, methodology): “Numerous CNN-based methods have also been applied in an endto-end fashion for image processing and generation problems, such as segmentation [24, 42], super-resolution [53, 22, 14, 15, 44], denoising [25, 49, 59, 47, 48], dehazing and deraining [32, 55], enhancement [31, 56] etc.”
Image De-Raining Transformer (2022, unknown): “…tasks [17], [18], [31], [32], [33], [34], [35], such as de-noising [36], [37], [38], super-resolution [39], [40], [41], de-blurring [42], [43], [44], [45], de-hazing [19], [19], [46], [47], [48], [49], [50], low-light image enhancement [51], [52], [53], [54], [55], style transfer [56], [57], etc .”
Deep Learning on Image Denoising: An overview (2019, unknown): “Automatic feature extraction methods can play a major role in reducing the computational costs for image applications [240, 179, 143].”