Oğuzhan Ulucan
Contact
Institut für Mathematik und Informatik
Walther-Rathenau-Str. 47
17489 Greifswald
Telefon: +49 3834 420 4623
Email: oguzhan.ulucan[at]uni-greifswald.de
Short Biography
Oguzhan Ulucan is a Ph.D. candidate and a research assistant at the University of Greifswald, Germany. He received his B.Sc. (with honors) and M.Sc. degree in electrical and electronics engineering from the Izmir University of Economics, Turkey, in 2017 and 2020, respectively. Under the supervision of Prof. Dr. Marc Ebner, he is doing research on computational color constancy and color illusion perception. In his thesis, he is developing algorithms that mimic the behavior of the human visual system on both color constancy and color illusion perception. His research interests also include intrinsic image decomposition, image fusion, and machine learning.
News
2024: Our work "A computational model for color assimilation illusions and color constancy" is accepted at ACCV 2024, Hanoi, Vietnam! I will be presenting it orally (oral presentation acceptance rate: 5.6%), and I am really excited for this opportunity!
2024: I have been selected as a reviewer for the IEEE SPS Multimedia Signal Processing Technical Committee! I am looking forward to contributing to the SPS community!
2024: Our work related to intrinsic image decomposition is now accesible at SN Computer Science!
2024: Two papers are accepted at CCIW 2024, Milano, Italy!
- Revisiting Color Constancy Using CNNs: Including Recent Observations
- Intrinsic Image Decomposition based on Retinex Theory, Superpixel Segmentation and Scale-Space Computations
2023: "Investigating Color Illusions from the Perspective of Computational Color Constancy" is accepted at VISAPP 2024, Rome, Italy!
2023: Our paper is accepted for publication in The International Journal of Computer Graphics - The Visual Computer!
Refereed Publications During the Ph.D.
* Please note that all papers which are available for download here are preprints.
A Scale-space Approach for Surface Normal Vector Estimation from Depth Maps (Invited Paper) [Paper]
Diclehan Ulucan, Oguzhan Ulucan, Marc Ebner
SN Computer Science, 2024
Multi-scale color constancy based on salient varying local spatial statistics [ Paper ]
Oguzhan Ulucan, Diclehan Ulucan, Marc Ebner
The Visual Computer, 2023
A computational model for color assimilation illusions and color constancy [ Paper ]
Oguzhan Ulucan, Diclehan Ulucan, Marc Ebner
ACCV 2024, Hanoi, Vietnam
Revisiting Color Constancy Using CNNs: Including Recent Observations [ Paper ]
Oguzhan Ulucan, Diclehan Ulucan, Marc Ebner
CCIW 2024, Milano, Italy
Intrinsic Image Decomposition based on Retinex Theory, Superpixel Segmentation and Scale-Space Computations [ Paper ]
Diclehan Ulucan, Oguzhan Ulucan, Marc Ebner
CCIW 2024, Milano, Italy
Investigating Color Illusions from the Perspective of Computational Color Constancy [ Paper ]
Oguzhan Ulucan, Diclehan Ulucan, Marc Ebner
VISAPP 2024, Rome, Italy
Multi-scale block-based color constancy [ Paper ]
Oguzhan Ulucan, Diclehan Ulucan, Marc Ebner
EUSIPCO 2023, Helsinki, Finland
CC-NORD: A Camera-inveriant global color constancy dataset [ Paper ]
Diclehan Ulucan, Oguzhan Ulucan, Marc Ebner
EUSIPCO 2023, Helsinki, Finland
Block-based color constancy: The deviation of the salient pixels [ Paper ] [ Poster ]
Oguzhan Ulucan, Diclehan Ulucan, Marc Ebner
IEEE ICASSP 2023, Rhodes Island, Greece
- Multi-scale surface normal estimation from depth maps (Best Student Paper Award Candidate) [Paper]
Diclehan Ulucan, Oguzhan Ulucan, Marc Ebner
IMPROVE 2023, Prague, Czech Republic
- Intrinsic Image Decomposition: Challenges and New Perspectives (Best Student Paper Award Candidate) [Paper]
Diclehan Ulucan, Oguzhan Ulucan, Marc Ebner
IMPROVE 2023, Prague, Czech Republic
BIO-CC: Biologically inspired color constancy [ Paper ] [ Poster ]
Oguzhan Ulucan, Diclehan Ulucan, Marc Ebner
BMVC 2022, London, UK
Color constancy beyond standard illuminants [ Paper ] [ Poster ]
Oguzhan Ulucan, Diclehan Ulucan, Marc Ebner
IEEE ICIP 2022, Bordeaux, France
- IID-NORD: A comprehensive intrinsic image decomposition dataset [Paper]
Diclehan Ulucan, Oguzhan Ulucan, Marc Ebner
IEEE ICIP 2022, Bordeaux, France
Teaching
Introduction to Computer Science (Tutorials)
Software Engineering Internship (Tutorials)
Introduction to Computer Science (Tutorials)
Evolutionary Algorithms (Tutorials)
Introduction to Computer Science (Tutorials)
Software Engineering Internship (Tutorials)
Introduction to Computer Science (Tutorials)
Academic Services
- Reviewer at International Journal of Computer Vision (2024)
- Reviewer at IEEE Transactions on Multimedia (2023-2024)
- Reviewer at IEEE Transactions on Image Processing (2023)
- Reviewer at IEEE Sensors Letters (2021 - 2022 - 2023)
- Reviewer at Imaging Science Journal (2024)
- Reviewer at IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2025), 06 - 11 April, Hyderabad, India, 2025.
- Reviewer at International Conference on Pattern Recognition (ICPR 2024), 01 - 05 April, Koltaka, India, 2024.
- Reviewer at IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2024), 14 - 19 April, Seoul, Korea, 2024.
- Reviewer at International Conference on Advances in Image Processing (ICAIP 2024), 18 - 20 October, Chengdu, China, 2024.
- Reviewer at International Conference on Advances in Image Processing (ICAIP 2023), 17 - 19 November, Beijing, China, 2023.
- 8th International Conference on Computer Graphics and Virtuality (ICCGV 2025) 21 – 23 February 2025, Chengdu, China.
- 8th International Conference on Advances in Image Processing (ICAIP 2024), 18 - 20 October 2024, Chengdu, China.
- 7th International Conference on Advances in Image Processing (ICAIP 2023), 17 - 19 November 2023, Beijing, China.
Color Assimilation Illusions
I am deeply interested in color assimilation illusions, which I believe can be beneficial tools for designing robust and simple-yet-effective artificial systems that mimic the human visual system.
In both our previous studies (Ulucan, Ulucan, and Ebner, 2022; Ulucan, Ulucan, and Ebner, 2024) and our recent work, which will be presented orally at ACCV 2024 in Hanoi, Vietnam, we have explicitly demonstrated that color assimilation illusions can be beneficial tools for computational color constancy. By utilizing these illusions, we can design or modify multi-illuminant color constancy methods, enhancing their performance in estimating the color of light sources for both simple and complex scenes.
Below are some examples of color assimilation illusions I have designed. In these illusions, the colors of the target regions (e.g., the triangles in the last image) are identical, yet they are perceived as different due to the context. i.e., their local surroundings. If you're interested in these illusions and would like to use them in your work, please feel free to contact me.
