{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T09:53:52Z","timestamp":1785405232503,"version":"3.56.0"},"reference-count":32,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T00:00:00Z","timestamp":1774915200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Science Foundation","award":["PHY-2229929"],"award-info":[{"award-number":["PHY-2229929"]}]},{"award":["PHY-2229929"],"award-info":[{"award-number":["PHY-2229929"]}],"id":[{"id":"https:\/\/ror.org\/021nxhr62","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>In visual object recognition problems, low light exposure and low-quality images present significant challenges in navigation, surveillance, and image retrieval applications, where reliable feature detection is critical. Although recent deep learning\u2013based image enhancement methods improve visual quality in the pixel domain, these improvements often do not translate to downstream machine vision performance, as important local gradient structures required for stable key point detection are frequently suppressed. In this work, we propose IllumiSIFT, a task-driven dark image enhancement framework that focuses on preserving Scale-Invariant Feature Transform (SIFT) key points by directly learning the Difference-of-Gaussian (DoG) pyramid from low-light image inputs. Unlike conventional pixel-level recovery approaches, the proposed method employs a cascaded residual learning architecture to predict Gaussian-blurred representations at multiple scales, enabling the generation of enhanced DoG images that are inherently aligned with the SIFT detection process. Extensive experiments conducted on the CDVS, Oxford Buildings, and Paris datasets demonstrate that the proposed approach consistently outperforms state-of-the-art enhancement methods in downstream SIFT matching performance under severe low-light conditions. These results confirm that gradient-domain, task-aligned enhancement provides a more effective and practical solution for recognition-centric low-light imaging applications.<\/jats:p>","DOI":"10.3390\/s26072147","type":"journal-article","created":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T13:23:17Z","timestamp":1774963397000},"page":"2147","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["IllumiSIFT: A Cascade Framework for DoG Pyramid Learning in Darkness"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3015-0056","authenticated-orcid":false,"given":"Dewan Fahim","family":"Noor","sequence":"first","affiliation":[{"name":"Electrical and Computer Engineering Department, Tuskegee University, Tuskegee, AL 36088, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7444-2173","authenticated-orcid":false,"given":"Mohammed Rashid","family":"Chowdhury","sequence":"additional","affiliation":[{"name":"CGI Inc., Ottawa, ON K1P 6A4, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sadia","family":"Sikder","sequence":"additional","affiliation":[{"name":"Pharmavite LLC, Opelika, AL 36801, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,3,31]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"2080","DOI":"10.1109\/TIP.2007.901238","article-title":"Image Denoising by Sparse 3-D Transform-Domain Collaborative Filtering","volume":"16","author":"Dabov","year":"2007","journal-title":"IEEE Trans. Image Process."},{"key":"ref_2","first-page":"1","article-title":"Contrast Enhancement Estimation for Digital Image Forensics","volume":"14","author":"Wen","year":"2018","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Chen, C., Chen, Q., Xu, J., and Koltun, V. (2018, January 18\u201323). Learning to See in the Dark. Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00347"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"2828","DOI":"10.1109\/TIP.2018.2810539","article-title":"Structure-Revealing Low-Light Image Enhancement Via Robust Retinex Model","volume":"27","author":"Li","year":"2018","journal-title":"IEEE Trans. Image Process."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"982","DOI":"10.1109\/TIP.2016.2639450","article-title":"LIME: Low-Light Image Enhancement via Illumination Map Estimation","volume":"26","author":"Guo","year":"2017","journal-title":"IEEE Trans. Image Process."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Maharjan, P., Li, L., Li, Z., Xu, N., Ma, C., and Li, Y. (2019, January 8\u201312). Improving Extreme Low-Light Image Denoising via Residual Learning. Proceedings of the 2019 IEEE International Conference on Multimedia and Expo (ICME), Shanghai, China.","DOI":"10.1109\/ICME.2019.00162"},{"key":"ref_7","first-page":"1","article-title":"Exploring Image Enhancement for Salient Object Detection in Low Light Images","volume":"17","author":"Xu","year":"2021","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3072959.3073592","article-title":"Deep bilateral learning for real-time image enhancement","volume":"36","author":"Gharbi","year":"2017","journal-title":"ACM Trans. Graph."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Moran, S., Marza, P., McDonagh, S., Parisot, S., and Slabaugh, G. (2020, January 13\u201319). DeepLPF: Deep Local Parametric Filters for Image Enhancement. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.01284"},{"key":"ref_10","first-page":"2058","article-title":"Learning Image-adaptive 3D Lookup Tables for High Performance Photo Enhancement in Real-time","volume":"44","author":"Zeng","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"10189","DOI":"10.1109\/TITS.2025.3550267","article-title":"VNDHR: Variational Single Nighttime Image Dehazing for Enhancing Visibility in Intelligent Transportation Systems via Hybrid Regularization","volume":"26","author":"Liu","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"9880","DOI":"10.1109\/TMM.2024.3400668","article-title":"CodedBGT: Code Bank-Guided Transformer for Low-Light Image Enhancement","volume":"26","author":"Ye","year":"2024","journal-title":"IEEE Trans. Multimed."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Hou, J., Zhu, Z., Hou, J., Liu, H., Zeng, H., and Yuan, H. (2023). Global structure-aware diffusion process for low-light image enhancement. Proceedings of the 37th International Conference on Neural Information Processing Systems, Curran Associates Inc.. NIPS \u201923.","DOI":"10.52202\/075280-3490"},{"key":"ref_14","first-page":"1","article-title":"Low-Light Image Enhancement with Wavelet-Based Diffusion Models","volume":"42","author":"Jiang","year":"2023","journal-title":"ACM Trans. Graph."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"131174","DOI":"10.1016\/j.neucom.2025.131174","article-title":"TransDiff: Transformer-based diffusion model for low-light image enhancement","volume":"655","author":"Zhang","year":"2025","journal-title":"Neurocomputing"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Sharif, S.M.A., Myrzabekov, A., Khujaev, N., Tsoy, R., Kim, S., and Lee, J. (2024, January 17\u201318). Learning Optimized Low-Light Image Enhancement for Edge Vision Tasks. Proceedings of the 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Seattle, WA, USA.","DOI":"10.1109\/CVPRW63382.2024.00639"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1016\/j.image.2019.02.001","article-title":"Low-light image enhancement using Gaussian Process for features retrieval","volume":"74","author":"Loh","year":"2019","journal-title":"Signal Process. Image Commun."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Wang, Z., Chang, S., Yang, Y., Liu, D., and Huang, T.S. (2016, January 27\u201330). Studying Very Low Resolution Recognition Using Deep Networks. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.518"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Ye, Z., Pei, Y., and Shi, J. (2009, January 11\u201313). An Adaptive Algorithm for Harris Corner Detection. Proceedings of the 2009 International Conference on Computational Intelligence and Software Engineering, Wuhan, China.","DOI":"10.1109\/CISE.2009.5366231"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1719","DOI":"10.1109\/TSMCB.2012.2228639","article-title":"A Generalized Laplacian of Gaussian Filter for Blob Detection and Its Applications","volume":"43","author":"Kong","year":"2013","journal-title":"IEEE Trans. Cybern."},{"key":"ref_21","unstructured":"Geng, C., and Jiang, X. (2009, January 8\u201311). SIFT features for face recognition. Proceedings of the 2009 2nd IEEE International Conference on Computer Science and Information Technology, Beijing, China."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Li, L., Li, Z., and Li, H. (2017, January 17\u201320). Visual query compression with locality preserving projection on Grassmann manifold. Proceedings of the 2017 IEEE International Conference on Image Processing (ICIP), Beijing, China.","DOI":"10.1109\/ICIP.2017.8296838"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Kher, H.R., and Thakar, V.K. (2014, January 8\u201310). Scale Invariant Feature Transform Based Image Matching and Registration. Proceedings of the 2014 Fifth International Conference on Signal and Image Processing, Bangalore, India.","DOI":"10.1109\/ICSIP.2014.12"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Rajkumar, R., and Singh, K.M. (2015, January 14\u201315). Digital image forgery detection using SIFT feature. Proceedings of the 2015 International Symposium on Advanced Computing and Communication (ISACC), Silchar, India.","DOI":"10.1109\/ISACC.2015.7377340"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Noor, D.F., Li, Y., Li, Z., Bhattacharyya, S., and York, G. (2019, January 12\u201317). Gradient Image Super-resolution for Low-resolution Image Recognition. Proceedings of the ICASSP 2019\u20142019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK.","DOI":"10.1109\/ICASSP.2019.8682436"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1016\/j.image.2019.06.013","article-title":"Multi-Scale Gradient Image Super-Resolution for Preserving SIFT Key Points in Low-Resolution Images","volume":"78","author":"Noor","year":"2019","journal-title":"Signal Process. Image Commun."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., and Sun, G. (2018, January 18\u201323). Squeeze-and-Excitation Networks. Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Agustsson, E., and Timofte, R. (2017, January 21\u201326). NTIRE 2017 Challenge on Single Image Super-Resolution: Dataset and Study. Proceedings of the The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Honolulu, HI, USA.","DOI":"10.1109\/CVPRW.2017.150"},{"key":"ref_29","unstructured":"PyTorch (2020, June 01). PyTorch Documentation. Available online: https:\/\/pytorch.org\/docs\/stable\/index.html."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Chandrasekhar, V., Chen, D., Tsai, S.S., Cheung, N.M., Chen, H., Takacs, G., Reznik, Y., Vedantham, R., Grzeszczuk, R., and Bach, J. (2011, January 23\u201325). The Stanford mobile visual search dataset. Proceedings of the ACM Multimedia Systems Conference (MMSys), San Jose, CA, USA.","DOI":"10.1145\/1943552.1943568"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Philbin, J., Chum, O., Isard, M., Sivic, J., and Zisserman, A. (2007, January 17\u201322). Object Retrieval with Large Vocabularies and Fast Spatial Matching. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Minneapolis, MN, USA.","DOI":"10.1109\/CVPR.2007.383172"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Philbin, J., Chum, O., Isard, M., Sivic, J., and Zisserman, A. (2008, January 23\u201328). Lost in Quantization: Improving Particular Object Retrieval in Large Scale Image Databases. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, AK, USA.","DOI":"10.1109\/CVPR.2008.4587635"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/7\/2147\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T04:14:59Z","timestamp":1775103299000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/7\/2147"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,31]]},"references-count":32,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["s26072147"],"URL":"https:\/\/doi.org\/10.3390\/s26072147","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,31]]}}}