Semantic-Aware Low-Light Image Enhancement by Learning from Multiple Color Spaces
Source abstract
Abstract
Extreme low-light image enhancement presents persistent challenges due to compounded degradations involving underexposure, sensor noise, and structural detail loss. Traditional low-light image enhancement methods predominantly employ global adjustment strategies that disregard semantic context, often resulting in incomplete detail recovery or color distortion. To address these limitations, we propose a semantic-aware knowledge-guided framework (SKF) that systematically integrates semantic priors for improved illumination recovery. Our framework introduces three key modules: A Semantic Feature Enhancement Module for integrating hierarchical semantic features, a Semantic-Guided Color Histogram Loss to enforce color consistency, and a Semantic-Guided Adversarial Loss to enhance perceptual realism. Furthermore, we improve the semantic-guided color histogram loss by leveraging multi-color space constraints. Inspired by human visual perception mechanisms, our enhanced loss function calculates color discrepancies across three color spaces—RGB, LAB, and LCH—through three components: lossrgb, losslab and losslch. These components collaboratively optimize image contrast and saturation, thereby simultaneously enhancing contrast preservation and chromatic naturalness.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Image Enhancement Techniques · Advanced Image Fusion Techniques · Advanced Image Processing Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Educational Science and Technology, Nanjing University of Posts and Telecommunications, Nanjing 210049, China
Key Laboratory of Flexible Electronics (KLOFE), School of Flexible Electronics (Future Technologies), Nanjing Tech University (NanjingTech), Nanjing 211816, China
Institute of Advanced Materials (IAM), Nanjing Tech University (NanjingTech), Nanjing 211816, China
Funding
National Natural Science Foundation of China
References (43)
Show source-provided references
1. A gray-level transformation-based method for image enhancement10.1016/S0167-8655(98)00109-3 ↗
2. Clahe-based low-light image enhancement for robust object detection in overhead power transmission system
3. Retinex-like Method for Image Enhancement in Poor Visibility Conditions10.1016/j.proeng.2011.08.527 ↗
4. Lamba, M., and Mitra, K. (2021, January 20–25). Restoring extremely dark images in real time. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.10.1109/CVPR46437.2021.00349 ↗
5. Maharjan, P., Li, L., Li, Z., Xu, N., Ma, C., and Li, Y. (2019, January 8–12). Improving extreme low-light image denoising via residual learning. Proceedings of the 2019 IEEE International Conference on Multimedia and Expo (ICME), Shanghai, China.10.1109/ICME.2019.00162 ↗
6. Chen, C., Chen, Q., Xu, J., and Koltun, V. (2018, January 18–23). Learning to see in the dark. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00347 ↗
7. Liang, D., Li, L., Wei, M., Yang, S., Zhang, L., Yang, W., Du, Y., and Zhou, H. (March, January 22). Semantically contrastive learning for low-light image enhancement. Proceedings of the AAAI Conference on Artificial Intelligence, Online.
8. Realization of the contrast limited adaptive histogram equalization (CLAHE) for real-time image enhancement10.1023/B:VLSI.0000028532.53893.82 ↗
9. Brightness preserving dynamic histogram equalization for image contrast enhancement10.1109/TCE.2007.4429280 ↗
10. A dynamic histogram equalization for image contrast enhancement10.1109/TCE.2007.381734 ↗
11. Image contrast and color enhancement using adaptive gamma correction and histogram equalization10.1016/j.ijleo.2019.02.054 ↗
12. Chiu, Y.S., Cheng, F.C., and Huang, S.C. (2011, January 9–12). Efficient contrast enhancement using adaptive gamma correction and cumulative intensity distribution. Proceedings of the 2011 IEEE International Conference on Systems, Man, and Cybernetics, Anchorage, AK, USA.10.1109/ICSMC.2011.6084119 ↗
13. A total variation model for retinex10.1137/100806588 ↗
14. A variational framework for retinex10.1023/A:1022314423998 ↗
15. LLNet: A deep autoencoder approach to natural low-light image enhancement10.1016/j.patcog.2016.06.008 ↗
16. MBLLEN: Low-Light Image/Video Enhancement Using CNNs
17. Zhang, Y., Zhang, J., and Guo, X. (2019, January 21–25). Kindling the darkness: A practical low-light image enhancer. Proceedings of the 27th ACM International Conference on Multimedia, Nice, France.10.1145/3343031.3350926 ↗
18. Beyond brightening low-light images10.1007/s11263-020-01407-x ↗
19. Zhu, M., Pan, P., Chen, W., and Yang, Y. (2020, January 7–12). Eemefn: Low-light image enhancement via edge-enhanced multi-exposure fusion network. Proceedings of the AAAI Conference on Artificial Intelligence, New York, NY, USA.10.1609/aaai.v34i07.7013 ↗
20. Luminance-aware pyramid network for low-light image enhancement10.1109/TMM.2020.3021243 ↗
21. Lightening network for low-light image enhancement10.1109/TIP.2020.3008396 ↗
22. DSLR: Deep stacked Laplacian restorer for low-light image enhancement10.1109/TMM.2020.3039361 ↗
23. Wang, C., Wu, H., and Jin, Z. (November, January 29). Fourllie: Boosting low-light image enhancement by fourier frequency information. Proceedings of the 31st ACM International Conference on Multimedia, Ottawa, ON, Canada.
24. Enlightengan: Deep light enhancement without paired supervision10.1109/TIP.2021.3051462 ↗
25. Yang, W., Wang, S., Fang, Y., Wang, Y., and Liu, J. (2020, January 13–19). From fidelity to perceptual quality: A semi-supervised approach for low-light image enhancement. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR42600.2020.00313 ↗
26. Zhang, L., Zhang, L., Liu, X., Shen, Y., Zhang, S., and Zhao, S. (2019, January 21–25). Zero-shot restoration of back-lit images using deep internal learning. Proceedings of the 27th ACM International Conference on Multimedia, Nice, France.10.1145/3343031.3351069 ↗
27. Zhu, A., Zhang, L., Shen, Y., Ma, Y., Zhao, S., and Zhou, Y. (2020, January 6–10). Zero-shot restoration of underexposed images via robust retinex decomposition. Proceedings of the 2020 IEEE International Conference on Multimedia and Expo (ICME), London, UK.10.1109/ICME46284.2020.9102962 ↗
28. Liu, R., Ma, L., Zhang, J., Fan, X., and Luo, Z. (2021, January 20–25). Retinex-inspired unrolling with cooperative prior architecture search for low-light image enhancement. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.10.1109/CVPR46437.2021.01042 ↗
29. Liu, D., Wen, B., Liu, X., Wang, Z., and Huang, T.S. (2017). When image denoising meets high-level vision tasks: A deep learning approach. arXiv.10.24963/ijcai.2018/117 ↗
30. Aakerberg, A., Johansen, A.S., Nasrollahi, K., and Moeslund, T.B. (2022, January 4–8). Semantic segmentation guided real-world super-resolution. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, Waikoloa, HI, USA.10.1109/WACVW54805.2022.00051 ↗
31. Wang, X., Yu, K., Dong, C., and Loy, C.C. (2018, January 18–23). Recovering realistic texture in image super-resolution by deep spatial feature transform. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00070 ↗
32. Fan, M., Wang, W., Yang, W., and Liu, J. (2020, January 12–16). Integrating semantic segmentation and retinex model for low-light image enhancement. Proceedings of the 28th ACM International Conference on Multimedia, Seattle, WA, USA.10.1145/3394171.3413757 ↗
33. Wu, Y., Pan, C., Wang, G., Yang, Y., Wei, J., Li, C., and Shen, H.T. (2023, January 17–24). Learning semantic-aware knowledge guidance for low-light image enhancement. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.10.1109/CVPR52729.2023.00166 ↗
34. Zhou, Z., Rahman Siddiquee, M.M., Tajbakhsh, N., and Liang, J. (2018, January 20). Unet++: A nested u-net architecture for medical image segmentation. Proceedings of the Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support: 4th International Workshop, DLMIA 2018, and 8th International Workshop, ML-CDS 2018, Granada, Spain. Proceedings 4.
35. Segnet: A deep convolutional encoder-decoder architecture for image segmentation10.1109/TPAMI.2016.2644615 ↗
36. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs10.1109/TPAMI.2017.2699184 ↗
37. Zhao, H., Shi, J., Qi, X., Wang, X., and Jia, J. (2017, January 21–26). Pyramid scene parsing network. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.660 ↗
38. Zamir, S.W., Arora, A., Khan, S., Hayat, M., Khan, F.S., and Yang, M.H. (2022, January 18–24). Restormer: Efficient transformer for high-resolution image restoration. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.10.1109/CVPR52688.2022.00564 ↗
39. Avi-Aharon, M., Arbelle, A., and Raviv, T.R. (2020). Deephist: Differentiable joint and color histogram layers for image-to-image translation. arXiv.
40. Globally and locally consistent image completion10.1145/3072959.3073659 ↗
41. Li, Y., Liu, S., Yang, J., and Yang, M.H. (2017, January 21–26). Generative face completion. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.624 ↗
42. Wei, C., Wang, W., Yang, W., and Liu, J. (2018). Deep Retinex Decomposition for Low-Light Enhancement. Proceedingss of the British Machine Vision Conference, Newcastle, UK, 3–6 September 2018, British Machine Vision Association.
43. Sparse Gradient Regularized Deep Retinex Network for Robust Low-Light Image Enhancement10.1109/TIP.2021.3050850 ↗