Sparse Gradient Regularized Deep Retinex Network for Robust Low-Light Image Enhancement
By Wenhan Yang, Wenjing Wang, Haofeng Huang, Jiaying Liu. IEEE Transactions on Image Processing, 2021
728 citations recorded by the source corpus.
Due to the absence of a desirable objective for low-light image enhancement, previous data-driven methods may provide undesirable enhanced results including amplified noise, degraded contrast and biased colors. In this work, inspired by Retinex theory, we design an end-to-end signal prior-guided layer separation and data-driven mapping network with layer-specified constraints for single-image low-light enhancement. A Sparse Gradient Minimization sub-Network (SGM-Net) is constructed to remove the low-amplitude structures and preserve major edge information, which facilitates extracting paired illumination maps of low/normal-light images. After the learned decomposition, two sub-networks (Enhance-Net and Restore-Net) are utilized to predict the enhanced illumination and reflectance maps, respectively, which helps stretch the contrast of the illumination map and remove intensive noise in the reflectance map. The effects of all these configured constraints, including the signal structure regularization and losses, combine together reciprocally, which leads to good reconstruction results in overall visual quality. The evaluation on both synthetic and real images, particularly on those containing intensive noise, compression artifacts and their interleaved artifacts, shows the effectiveness of our novel models, which significantly outperforms the state-of-the-art methods.
Subfields: Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/d1550954e9793d61736d519d0e0fa2085d354d79
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
- Chen Change Loy
- Luc Van Gool
- Radu Timofte
- Ming-Hsuan Yang
- Yulun Zhang
- Lei Zhang
- Jiaya Jia
- Xiaogang Wang
Citations in the corpus
- Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement (2023, methodology): “Our Retinexformer significantly advances state-of-theart Retinex-based deep learning methods including DUPE (DeepUPE [48]), ReNet (RetinexNet [53]), KinD [65], and RUAS [31] on six low-light image enhancement benchmarks: LOL-v1 [53], LOL-v2 [58]-real, LOL-v2 [58]-synthetic, SID [8], SMID [9], and SD”
- Low-Light Image and Video Enhancement Using Deep Learning: A Survey (2021, background): “[17], LPNet [18], DLN [19], TBEFN [20], DSLR [21], Zhang et al. [22], PRIEN [23], and Retinex-Net [24].”
- SNR-Aware Low-light Image Enhancement (2022, methodology): “RF [24] 3DLUT [60] A3DLUT [42] Band [52] EG [20] Retinex [29] Sparse [53] IPT [6] Uformer [44 RF [24] 3DLUT [60] A3DLUT [42] Band [52] EG [20] Retinex [29] Sparse [53] IPT [6] Uformer [44 RF [24] 3DLUT [60] A3DLUT [42] Band [52] EG [20] Retinex [29] Sparse [53] IPT [6] Uformer [44 Ratio (PSNR) and S”