前一段整理了近几年的弱光图像的相关论文和代码,故在这里做一个汇总,以方便大家和有需要的同学们查阅。(这里整理的主要是基于深度学习的方法)
常用数据集:
一、Paired
1、LOL(500张):https://daooshee.github.io/BMVCwebsite/
Cite from:Wei C, Wang W, Yang W, et al. Deep retinex decomposition for low-light enhancement[J]. arXiv preprint arXiv:1808.04560, .
2、SCIE(4413张):/csjcai/SICE
Cite from:Cai J, Gu S, Zhang L. Learning a deep single image contrast enhancer from multi-exposure images[J]. IEEE Transactions on Image Processing, , 27(4): 2049-2062.
3、SID(5094张):/cchen156/Learning-to-See-in-the-Dark
Cite from:Chen C, Chen Q, Xu J, et al. Learning to see in the dark[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. : 3291-3300.
二、Unpaired
1、LIME(10张):/file/d/0BwVzAzXoqrSXb3prWUV1YzBjZzg/view
Cite from:Guo X, Li Y, Ling H. LIME: Low-light image enhancement via illumination map estimation[J]. IEEE Transactions on image processing, , 26(2): 982-993.
2、NPE(84张):/drive/folders/1lp6m5JE3kf3M66Dicbx5wSnvhxt90V4T
Cite from:Wang S, Zheng J, Hu H M, et al. Naturalness preserved enhancement algorithm for non-uniform illumination images[J]. IEEE transactions on image processing, , 22(9): 3538-3548.
3、MEF(17张):/drive/folders/1lp6m5JE3kf3M66Dicbx5wSnvhxt90V4T
Cite from:Ma K, Zeng K, Wang Z. Perceptual quality assessment for multi-exposure image fusion[J]. IEEE Transactions on Image Processing, , 24(11): 3345-3356.
4、DICM(64张):/drive/folders/1lp6m5JE3kf3M66Dicbx5wSnvhxt90V4T
Cite from:C. Lee, C. Lee and C. -S. Kim, “Contrast enhancement based on layered difference representation,” 19th IEEE International Conference on Image Processing, , pp. 965-968, doi: 10.1109/ICIP..6467022.
5、VV(24张):/drive/folders/1lp6m5JE3kf3M66Dicbx5wSnvhxt90V4T
Cite from:Vonikakis V, Andreadis I, Gasteratos A. Fast centre–surround contrast modification[J]. IET Image processing, , 2(1): 19-34.
论文汇总:
【】
1、(_CVPR)Toward Fast, Flexible, and Robust Low-Light Image Enhancement
Cite from:Ma L, Ma T, Liu R, et al. Toward Fast, Flexible, and Robust Low-Light Image Enhancement[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. : 5637-5646.
【Paper】【Code_PyTorch】
2、(_CVPR)URetinex-Net: Retinex-Based Deep Unfolding Network for Low-Light Image Enhancement
Cite from:Wu W, Weng J, Zhang P, et al. URetinex-Net: Retinex-Based Deep Unfolding Network for Low-Light Image Enhancement[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. : 5901-5910.
【Paper】【Code_Pytorch】
3、(_CVPR)SNR-aware Low-Light Image Enhancement
Cite from:Xu X, Wang R, Fu C W, et al. SNR-Aware Low-Light Image Enhancement[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. : 17714-17724.
【Paper】【Code_Pytorch】
【】
1、(_CVPR)Learning to restore low-light images via decomposition-and-enhancemen
Cite from:Xu K, Yang X, Yin B, et al. Learning to restore low-light images via decomposition-and-enhancement[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. : 2281-2290.
【Paper】【Code】
2、(_CVPR)Zero-reference deep curve estimation for low-light image enhancement
Cite from:Guo C, Li C, Guo J, et al. Zero-reference deep curve estimation for low-light image enhancement[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. : 1780-1789.
【Paper】【Code_Pytorch】
3、(_CVPR)From fidelity to perceptual quality: A semi-supervised approach for low-light image enhancement
Cite from:Yang W, Wang S, Fang Y, et al. From fidelity to perceptual quality: A semi-supervised approach for low-light image enhancement[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. : 3063-3072.
【Paper】【Code】
4、(_ACMMM)Integrating semantic segmentation and retinex model for low light image enhancement
Cite from:Fan M, Wang W, Yang W, et al. Integrating semantic segmentation and retinex model for low-light image enhancement[C]//Proceedings of the 28th ACM international conference on multimedia. : 2317-2325.
【Paper 】【Code】
5、(_AAAI)EEMEFN: Low-light image enhancement via edge-enhanced multi-exposure fusion network
Cite from:Zhu M, Pan P, Chen W, et al. Eemefn: Low-light image enhancement via edge-enhanced multi-exposure fusion network[C]//Proceedings of the AAAI Conference on Artificial Intelligence. , 34(07): 13106-13113.
【Paper】【Code】
【】
1、(_ICCV)Seeing motion in the dark
Cite from:Chen C, Chen Q, Do M N, et al. Seeing motion in the dark[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. : 3185-3194.
【Paper】【Code_TensorFlow】
2、(_CVPR)Underexposed Photo Enhancement Using Deep Illumination Estimation
Cite from:Wang R, Zhang Q, Fu C W, et al. Underexposed photo enhancement using deep illumination estimation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. : 6849-6857.
【Paper】【Code_TensorFlow】
3、(_ACMMM)Zero-shot restoration of back-lit images using deep internal learning
Cite from:Zhang L, Zhang L, Liu X, et al. Zero-shot restoration of back-lit images using deep internal learning[C]//Proceedings of the 27th ACM International Conference on Multimedia. : 1623-1631.
【Paper 】【Code_TensorFlow】
4、(_ACMMM)Kindling the Darkness: A Practical Low-light Image Enhancer
Cite from:Zhang Y, Zhang J, Guo X. Kindling the darkness: A practical low-light image enhancer[C]//Proceedings of the 27th ACM international conference on multimedia. : 1632-1640.
【Paper 】【Code_TensorFlow】
5、(_TIP)EnlightenGAN: Deep light enhancement without paired supervision
Cite from:Jiang Y, Gong X, Liu D, et al. Enlightengan: Deep light enhancement without paired supervision[J]. IEEE Transactions on Image Processing, , 30: 2340-2349.
【Paper】【Code】
6、(_TIP)Low-light image enhancement via a deep hybrid network
Cite from:Ren W, Liu S, Ma L, et al. Low-light image enhancement via a deep hybrid network[J]. IEEE Transactions on Image Processing, , 28(9): 4364-4375.
【Paper】【Code】
7、(_ACMMM)Progressive retinex: Mutually reinforced illumination-noise perception network for low-light image enhancement
Cite from:Wang Y, Cao Y, Zha Z J, et al. Progressive retinex: Mutually reinforced illumination-noise perception network for low-light image enhancement[C]//Proceedings of the 27th ACM international conference on multimedia. : -.
【Paper 】【Code_Pytorch】
【】
1、(_BMVC)MBLLEN: Low-light Image/Video Enhancement Using CNNs
Cite from:Lv F, Lu F, Wu J, et al. MBLLEN: Low-Light Image/Video Enhancement Using CNNs[C]//BMVC. , 220(1): 4.
【Paper】【Code_TensorFlow】
2、(_PRL)LightenNet: A convolutional neural network for weakly illuminated image enhancement
Cite from:Li C, Guo J, Porikli F, et al. LightenNet: A convolutional neural network for weakly illuminated image enhancement[J]. Pattern recognition letters, , 104: 15-22.
【Paper】【Code_Caffe&Matlab】
3、(_BMVC)Deep retinex decomposition for low-light enhancement
Cite from:Wei C, Wang W, Yang W, et al. Deep retinex decomposition for low-light enhancement[J]. arXiv preprint arXiv:1808.04560, .
【Paper】【Code_TensorFlow】
4、(_TIP)Learning a deep single image contrast enhancer from multi-exposure images
Cite from:Cai J, Gu S, Zhang L. Learning a deep single image contrast enhancer from multi-exposure images[J]. IEEE Transactions on Image Processing, , 27(4): 2049-2062.
【Paper】【Code_Caffe&Matlab】
5、(_CVPR)Learning to see in the dark
Cite from:Chen C, Chen Q, Xu J, et al. Learning to see in the dark[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. : 3291-3300.
【Paper】【Code_TensorFlow】
6、(_NeurIPS)DeepExposure: Learning to expose photos with asynchronously reinforced adversarial learning
Cite from:Yu R, Liu W, Zhang Y, et al. Deepexposure: Learning to expose photos with asynchronously reinforced adversarial learning[J]. Advances in Neural Information Processing Systems, , 31.
【Paper】【Code_暂无】
【】
1、(_TOG)Deep Bilateral Learning for Real-Time Image Enhancement (HDR-Net)
Cite from:Gharbi M, Chen J, Barron J T, et al. Deep bilateral learning for real-time image enhancement[J]. ACM Transactions on Graphics (TOG), , 36(4): 1-12.
【Paper】【Code】
2、(_PR)LLNet: A deep autoencoder approach to natural low-light image enhancement
Cite from:Lore K G, Akintayo A, Sarkar S. LLNet: A deep autoencoder approach to natural low-light image enhancement[J]. Pattern Recognition, , 61: 650-662.
【Paper】【Code_Theano】