Levent Karacan

Gaziantep University. Department of Computer Engineering

levent.png

Department of Computer Engineering

Gaziantep University

Gaziantep, Türkiye

I am currently affiliated with Department of Computer Engineering at Gaziantep University, Gaziantep, Türkiye as an assistant professor. Prior to joining here, I was a faculty member of Department of Computer Engineering at Iskenderun Technical University for 3 years (2020 - 2023). I obtained my Ph.D.(2019) and M.Sc.(2013) degrees from the Department of Computer Engineering at Hacettepe University, under the supervision of Aykut Erdem and Erkut Erdem. During my Ph.D., I had the opportunity to visit the Amsterdam Machine Learning Lab, University of Amsterdam (UvA), Netherlands to work with Zeynep Akata from October 2018 to January 2019.

My primary research interests are centered around image and video processing, with a focus on leveraging deep learning, particularly through deep generative models. I am highly enthusiastic about exploring innovative approaches to address a broad spectrum of challenges within the domains of computer vision and computer graphics such as camera localization, video stabilization, object goal navigation, etc. I am open to collaborations aimed at tackling the diverse challenges in these exciting fields and contributing to advancements.

news

Oct 02, 2024 Our paper on extremely low-light burst image enhancement is accepted for publication in Journal of Real-time Image Processing (SCI-E Q2): “Illuminate the Night: Lightweight Fusion and Enhancement Model for Extreme Low-Light Burst Images”. To appear
Mar 26, 2024 Our paper on video stabilization is accepted for publication in Computational Visual Media: “VidStabFormer: Full-frame Video Stabilization via Spatiotemporal Transformers”. To appear
Nov 02, 2023 My new paper on multi-focus image fusion has been published in IEEE Access (SCI (Q2)): Trainable self-guided filter for multi-focus image fusion .
Sep 20, 2023 My paper on multi-focus image fusion has been published in Signal Processing:Image Communication (SCI (Q2)): Multi-image transformer for multi-focus image fusion.
Jul 26, 2023 Our paper on video editing is accepted to ICCV 2023: “VidStyleODE: Disentangled Video Editing via StyleGAN and NeuralODEs”. Read more about our paper at our project website.

selected publications

  1. motivation.png
    Multi-image transformer for multi-focus image fusion
    Levent Karacan
    Signal Processing: Image Communication, 2023
  2. motivation_recoloc.png
    Region contrastive camera localization
    Mehmet Sarıgül, and Levent Karacan
    Pattern Recognition Letters, 2023
  3. tsgf-gan.png
    Trainable Self-Guided Filter for Multi-Focus Image Fusion
    Levent Karacan
    IEEE Access, 2023
  4. dicomogan.gif
    Disentangling Content and Motion for Text-Based Neural Video Manipulation
    Levent Karacan, Tolga Kerimoğlu, İsmail Ata İnan , and 3 more authors
    In British Machine Vision Conference (BMVC) , 2022
  5. attribute_hallucination.png
    Manipulating attributes of natural scenes via hallucination
    Levent Karacan, Zeynep Akata, Aykut Erdem , and 1 more author
    ACM Transactions on Graphics (TOG), 2019
  6. mri_gan.png
    Image synthesis in multi-contrast MRI with conditional generative adversarial networks
    Salman UH Dar, Mahmut Yurt, Levent Karacan , and 3 more authors
    IEEE transactions on medical imaging, 2019
  7. alpha_matte.png
    Alpha matting with kl-divergence-based sparse sampling
    Levent Karacan, Aykut Erdem, and Erkut Erdem
    IEEE Transactions on Image Processing, 2017
  8. image_matte.png
    Image matting with KL-divergence based sparse sampling
    Levent Karacan, Aykut Erdem, and Erkut Erdem
    In Proceedings of the IEEE international conference on computer vision , 2015
  9. smooth.png
    Structure-preserving image smoothing via region covariances
    Levent Karacan, Erkut Erdem, and Aykut Erdem
    ACM Transactions on Graphics (TOG), 2013