Prof. Cosmin Ancuti ETcTI, University Politehnica Timisoara 2 Vasile Parvan Blvd., 300223,  Timisoara, Romania This email address is being protected from spambots. You need JavaScript enabled to view it.

Cosmin Ancuți received his Ph.D. from Hasselt University, Belgium, in 2009. From 2010 to 2012, he held postdoctoral research positions at iMinds and the Intel ExaScience Laboratory at imec in Leuven, Belgium. He later served as a Marie Skłodowska-Curie Research Fellow at the Université catholique de Louvain, Belgium, from 2015 to 2017. He is currently a Full Professor in the Faculty of ETcTI at Politehnica University Timișoara, Romania. Since 2020, Cosmin Ancuți has been ranked among the world’s top 2% of researchers in the Stanford University–Elsevier classification. He has authored or co-authored more than 70 papers published in leading journals and conference proceedings. He is also a co-organizer of the IEEE CVPR NTIRE workshop. In 2020, he received the “Gheorghe Cartianu” Award from the Romanian Academy. His research interests include image and video enhancement, computer vision, and  artificial intelligence.

Google scholar: https://scholar.google.com/citations?user=zVTgt8IAAAAJ&hl=en

Selected Research Projects (Principal Investigator):

• “Affordable Autonomous Underwater Vehicle (AUV) for search, inspection and maintenance operations in turbid underwater”- PED (2017-2018) (PN-III-P2-2.1-PED-2016-0940) - UEFISCDI , University Politehnica Timisoara, Romania;
• "Inspection of highly scattered and artificially illuminated underwater scenes using OpenROV Trident", PED (2020-2022) (PN-III-P2-2.1-PED-2019-2805)-UEFISCDI, University Politehnica Timisoara, Romania;
• “Advanced OCR techniques for printed documents”, Tecniospring Plus (2018-2020) (TECSPR17-1-0054) - ACCIO, University of Girona, Spain;
• “A robust regression learning framework with application in aerial image restoration and microscopy image analysis”- Move-in-Louvain (2015-2017)- Grant co-financed by Marie Skłodowska-Curie EU programme: University Catholique of Louvain, Belgium;
• “Dataset and dehazing methods for non-homogeneous and dense hazy scenes”, (2021-2023) Individual Fellowship Marie Skłodowska-Curie EU (UC Louvain, Belgium);

Selected publications:

• Cosmin Ancuti , C.O. Ancuti, C. De Vleeschouwer, P. Bekaert, “Color balance and fusion for underwater image enhancement”, IEEE Transactions on Image Processing, 2018
• O. Ancuti, Cosmin Ancuti , R. Timofte, C. De Vleeschouwer, “O-HAZE: a dehazing benchmark with real hazy and haze-free outdoor images” IEEE Conference on Computer Vision and Pattern Recog. (CVPRW), 2018
• , T. Mu, C.O. Ancuti, Cosmin Ancuti “Multinex: Lightweight Low-light Image Enhancement via Multi-prior Retinex”. IEEE/CVF Conf. on Comp. Vision and Pattern Recog. (CVPR), Denver, US, 2026
• Balmez, A. Brateanu, C. Orhei, C.O. Ancuti, Cosmin Ancuti, “ISALUX: Illumination and semantics-aware transformer employing mixture of experts for low light image enhancement” Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Tucson, US, 2026
• Liu, T. Li, C. Tan, W. Ren, Cosmin Ancuti, W. Lin “IHDCP: Single Image Dehazing Using Inverted Haze Density Correction Prior”. IEEE Transactions on Image Processing, 2026
• P. Ancuti, A. Brateanu, C.O. Ancuti, R. Timofte, Cosmin Ancuti, “NT-HAZE: A Benchmark Dataset for Realistic Night-time Image Dehazing” IEEE/CVF Conf. on Comp. Vision and Pattern Recog. (CVPR), 2026
• Brateanu, R. Balmez, A. Avram, C. Orhei, Cosmin Ancuti, “LYT-NET: Lightweight YUV Transformer-based Network for Low-light Image Enhancement”, IEEE Signal Processing Letters, 2025
• Cosmin Ancuti , C.O. Ancuti, C. De Vleeschouwer, A.C. Bovik, “Day and night-time dehazing by local airlight estimation”, IEEE Transactions on Image Processing, 2020
• Cosmin Ancuti , C.O. Ancuti, C. De Vleeschouwer, M. Sbert, “Color Channel Compensation (3C): A fundamental pre-processing step for image enhancement” IEEE Transactions on Image Processing, 2020
• O. Ancuti, Cosmin Ancuti, C. De Vleeschouwer, A.C. Bovik, “ Single-scale fusion: An effective approach to merging images”, IEEE Transactions on Image Processing, 2017