{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:40:42Z","timestamp":1781534442781,"version":"3.54.5"},"reference-count":48,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T00:00:00Z","timestamp":1776816000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100014883","name":"China National Nuclear Corporation","doi-asserted-by":"publisher","award":["CNI23-W-KY-2024-01"],"award-info":[{"award-number":["CNI23-W-KY-2024-01"]}],"id":[{"id":"10.13039\/501100014883","id-type":"DOI","asserted-by":"publisher"}]},{"award":["CNI23-W-KY-2024-01"],"award-info":[{"award-number":["CNI23-W-KY-2024-01"]}],"id":[{"id":"https:\/\/ror.org\/01d5ymp84","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computers"],"abstract":"<jats:p>Extreme low-light image enhancement (ELLIE) targets the restoration of visual quality under ultra-dim environments (&lt;0.1 lux). Conventional image signal processing (ISP) pipelines often fail in such scenarios due to the limitations of heuristic, hand-crafted algorithms. While deep learning has advanced the field via end-to-end mapping, existing models suffer from constrained generalization and suboptimal perceptual fidelity, primarily stemming from the scarcity of large-scale, high-diversity datasets. To bridge this gap, we present the Day and Night (DaN) dataset, a semi-synthetic benchmark synthesized through a rigorous physics-based noise model. This approach effectively captures authentic noise characteristics while enabling the scalable generation of paired samples across multifaceted illumination conditions and scenes. Furthermore, we propose No Longer Vigil (NLV), a fully differentiable AI-ISP framework. By replacing traditional rigid blocks with adaptive non-linear networks, NLV facilitates scene-dependent transformations without requiring manual priors. Comprehensive evaluations demonstrate that our method significantly outshines state-of-the-art approaches, yielding a 4.15 dB gain in PSNR and a 0.026 improvement in SSIM.<\/jats:p>","DOI":"10.3390\/computers15050261","type":"journal-article","created":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T09:01:24Z","timestamp":1776848484000},"page":"261","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DaN: A Comprehensive Semi-Real Dataset for Extreme Low-Light Image Enhancement"],"prefix":"10.3390","volume":"15","author":[{"given":"Qiuyang","family":"Sun","sequence":"first","affiliation":[{"name":"China Nuclear Industry 23 Construction Co., Ltd., Beijing 100080, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3997-4670","authenticated-orcid":false,"given":"Shaonan","family":"Liu","sequence":"additional","affiliation":[{"name":"Cyberspace Security Institute, Beijing University of Posts and Telecommunications, Beijing 100876, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hong","family":"Li","sequence":"additional","affiliation":[{"name":"China Nuclear Industry 23 Construction Co., Ltd., Beijing 100080, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingchao","family":"Feng","sequence":"additional","affiliation":[{"name":"China Nuclear Industry 23 Construction Co., Ltd., Beijing 100080, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liuqing","family":"Sun","sequence":"additional","affiliation":[{"name":"China Nuclear Industry 23 Construction Co., Ltd., Beijing 100080, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kun","family":"Lu","sequence":"additional","affiliation":[{"name":"China Nuclear Industry 23 Construction Co., Ltd., Beijing 100080, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kangtai","family":"Liu","sequence":"additional","affiliation":[{"name":"China Nuclear Industry 23 Construction Co., Ltd., Beijing 100080, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,4,22]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1080\/03091900512331333158","article-title":"A perspective on medical infrared imaging","volume":"29","author":"Jiang","year":"2005","journal-title":"J. Med. Eng. Technol."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"429","DOI":"10.3758\/BF03195520","article-title":"Infrared imaging technology and biological applications","volume":"35","author":"Kastberger","year":"2003","journal-title":"Behav. Res. Methods Instrum. Comput."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Diakides, N.A., and Bronzino, J.D. (2007). Advances in medical infrared imaging. Medical Infrared Imaging, CRC Press.","DOI":"10.1201\/9781420008340"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"461","DOI":"10.1002\/wnan.77","article-title":"Near infrared imaging with nanoparticles","volume":"2","author":"Adair","year":"2010","journal-title":"Wiley Interdiscip. Rev. Nanomed. Nanobiotechnol."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"T\u00fcrker-Kaya, S., and Huck, C.W. (2017). A review of mid-infrared and near-infrared imaging: Principles, concepts and applications in plant tissue analysis. Molecules, 22.","DOI":"10.3390\/molecules22010168"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"168","DOI":"10.1117\/12.484800","article-title":"Color the night: Applying daytime colors to nighttime imagery","volume":"Volume 5081","author":"Toet","year":"2003","journal-title":"Proceedings of the Enhanced and Synthetic Vision 2003"},{"key":"ref_7","first-page":"65","article-title":"True-color night vision cameras","volume":"Volume 6540","author":"Kriesel","year":"2007","journal-title":"Proceedings of the Optics and Photonics in Global Homeland Security III"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Liu, S., Feng, C., Wang, X., Wang, H., Zhu, R., Li, Y., and Lei, L. (2022). Deep-flexisp: A three-stage framework for night photography rendering. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPRW56347.2022.00128"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Zini, S., Rota, C., Buzzelli, M., Bianco, S., and Schettini, R. (2023). Back to the future: A night photography rendering ISP without deep learning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPRW59228.2023.00151"},{"key":"ref_10","first-page":"470","article-title":"Research on starlight level broad spectrum full color imaging technology","volume":"Volume 11338","author":"Yang","year":"2019","journal-title":"Proceedings of the AOPC 2019: Optical Sensing and Imaging Technology, 2019"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Toet, A. (2003). Applying daytime colors to multiband nightvision imagery. Proceedings of the Sixth International Conference on Information Fusion (FUSION), SPIE.","DOI":"10.1109\/ICIF.2003.177503"},{"key":"ref_12","first-page":"276","article-title":"Perceptual evaluation of colorized nighttime imagery","volume":"Volume 9014","author":"Toet","year":"2014","journal-title":"Proceedings of the Human Vision and Electronic Imaging XIX, 2014"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Zuo, W., Zhang, L., Song, C., and Zhang, D. (2013). Texture enhanced image denoising via gradient histogram preservation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR.2013.159"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"4608","DOI":"10.1109\/TIP.2018.2839891","article-title":"FFDNet: Toward a fast and flexible solution for CNN-based image denoising","volume":"27","author":"Zhang","year":"2018","journal-title":"IEEE Trans. Image Process."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Guo, S., Yan, Z., Zhang, K., Zuo, W., and Zhang, L. (2019). Toward convolutional blind denoising of real photographs. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR.2019.00181"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1934","DOI":"10.1109\/TPAMI.2022.3167175","article-title":"Learning enriched features for fast image restoration and enhancement","volume":"45","author":"Zamir","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_17","first-page":"8520","article-title":"Physics-based noise modeling for extreme low-light photography","volume":"44","author":"Wei","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Chen, C., Chen, Q., Xu, J., and Koltun, V. (2018). Learning to see in the dark. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR.2018.00347"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Wei, K., Fu, Y., Yang, J., and Huang, H. (2020). A physics-based noise formation model for extreme low-light raw denoising. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR42600.2020.00283"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Qin, H., Wang, X., and Li, H. (2021). Rethinking noise synthesis and modeling in raw denoising. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), IEEE.","DOI":"10.1109\/ICCV48922.2021.00455"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Moran, N., Schmidt, D., Zhong, Y., and Coady, P. (2020). Noisier2noise: Learning to denoise from unpaired noisy data. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR42600.2020.01208"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Calvarons, A.F. (2021). Improved Noise2Noise denoising with limited data. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPRW53098.2021.00089"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Zhang, C., Han, W., Zhou, Y., Shen, J., Xu, C.Z., and Liu, W. (2024). Leveraging Frame Affinity for sRGB-to-RAW Video De-rendering. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR52733.2024.02424"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"2072","DOI":"10.1109\/TIP.2021.3050850","article-title":"Sparse Gradient Regularized Deep Retinex Network for Robust Low-Light Image Enhancement","volume":"30","author":"Yang","year":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Cai, Y., Bian, H., Lin, J., Wang, H., Timofte, R., and Zhang, Y. (2023). Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), IEEE.","DOI":"10.1109\/ICCV51070.2023.01149"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Jin, X., Han, L.H., Li, Z., Guo, C.L., Chai, Z., and Li, C. (2023). Dnf: Decouple and feedback network for seeing in the dark. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR52729.2023.01739"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Abdelhamed, A., Brubaker, M.A., and Brown, M.S. (2019). Noise flow: Noise modeling with conditional normalizing flows. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), IEEE.","DOI":"10.1109\/ICCV.2019.00326"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Zamir, S.W., Arora, A., Khan, S., Hayat, M., Khan, F.S., Yang, M.H., and Shao, L. (2020). Cycleisp: Real image restoration via improved data synthesis. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR42600.2020.00277"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Jang, G., Lee, W., Son, S., and Lee, K.M. (2021). C2n: Practical generative noise modeling for real-world denoising. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), IEEE.","DOI":"10.1109\/ICCV48922.2021.00235"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Wang, Y., Huang, H., Xu, Q., Liu, J., Liu, Y., and Wang, J. (2020). Practical deep raw image denoising on mobile devices. Proceedings of the European Conference on Computer Vision (ECCV), Springer.","DOI":"10.1007\/978-3-030-58539-6_1"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Maleky, A., Kousha, S., Brown, M.S., and Brubaker, M.A. (2022). Noise2noiseflow: Realistic camera noise modeling without clean images. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR52688.2022.01711"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Kousha, S., Maleky, A., Brown, M.S., and Brubaker, M.A. (2022). Modeling srgb camera noise with normalizing flows. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR52688.2022.01694"},{"key":"ref_33","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., and Belongie, S. (2011). The Caltech-Ucsd Birds-200-2011 Dataset, California Institute of Technology. Technical Report."},{"key":"ref_34","unstructured":"Khosla, A., Jayadevaprakash, N., Yao, B., and Li, F.F. (2011). Novel dataset for fine-grained image categorization: Stanford dogs. Proceedings of the CVPR Workshop on Fine-Grained Visual Categorization (FGVC), IEEE."},{"key":"ref_35","unstructured":"Wei, C., Wang, W., Yang, W., and Liu, J. (2018). Deep Retinex Decomposition for Low-Light Enhancement. arXiv."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"370","DOI":"10.1109\/TPAMI.2023.3301502","article-title":"Learnability enhancement for low-light raw image denoising: A data perspective","volume":"46","author":"Feng","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Wang, Y., Yu, Y., Yang, W., Guo, L., Chau, L.P., Kot, A.C., and Wen, B. (2023). Exposurediffusion: Learning to expose for low-light image enhancement. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), IEEE.","DOI":"10.1109\/ICCV51070.2023.01143"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Jin, X., Xiao, J.W., Han, L.H., Guo, C., Zhang, R., Liu, X., and Li, C. (2023). Lighting every darkness in two pairs: A calibration-free pipeline for raw denoising. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), IEEE.","DOI":"10.1109\/ICCV51070.2023.01221"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Lamba, M., and Mitra, K. (2021). Restoring extremely dark images in real time. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR46437.2021.00349"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Monakhova, K., Richter, S.R., Waller, L., and Koltun, V. (2022). Dancing under the stars: Video denoising in starlight. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR52688.2022.01576"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Zheng, N., Zhou, M., Dong, Y., Rui, X., Huang, J., Li, C., and Zhao, F. (2023). Empowering low-light image enhancer through customized learnable priors. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), IEEE.","DOI":"10.1109\/ICCV51070.2023.01154"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Hore, A., and Ziou, D. (2010). Image quality metrics: PSNR vs. SSIM. Proceedings of the 20th International Conference on Pattern Recognition (ICPR), ACM.","DOI":"10.1109\/ICPR.2010.579"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"8","DOI":"10.4236\/jcc.2019.73002","article-title":"Image quality assessment through FSIM, SSIM, MSE and PSNR\u2014A comparative study","volume":"7","author":"Sara","year":"2019","journal-title":"J. Comput. Commun."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"671","DOI":"10.1109\/34.141557","article-title":"An analysis of camera noise","volume":"14","author":"Boie","year":"1992","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/S0370-1573(99)00123-4","article-title":"Shot noise in mesoscopic conductors","volume":"336","author":"Blanter","year":"2000","journal-title":"Phys. Rep."},{"key":"ref_46","unstructured":"Sch\u00f6berl, M., Senel, C., F\u00f6\u00dfel, S., Bloss, H., and Kaup, A. (2009). Non-linear dark current fixed pattern noise compensation for variable frame rate moving picture cameras. Proceedings of the 17th European Signal Processing Conference (EUSIPCO), IEEE."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1016\/j.jvcir.2018.01.012","article-title":"Renoir\u2014A dataset for real low-light image noise reduction","volume":"51","author":"Anaya","year":"2018","journal-title":"J. Vis. Commun. Image Represent."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Weng, C.C., Chen, H., and Fuh, C.S. (2005). A novel automatic white balance method for digital still cameras. Proceedings of the 2005 IEEE International Symposium on Circuits and Systems (ISCAS), IEEE.","DOI":"10.1109\/ISCAS.2005.1465458"}],"container-title":["Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-431X\/15\/5\/261\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T09:25:39Z","timestamp":1776849939000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-431X\/15\/5\/261"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,22]]},"references-count":48,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5]]}},"alternative-id":["computers15050261"],"URL":"https:\/\/doi.org\/10.3390\/computers15050261","relation":{},"ISSN":["2073-431X"],"issn-type":[{"value":"2073-431X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,22]]}}}