Ayşegül Dündar
Asst. Prof. at Bilkent University
Ankara, Turkey

Google Scholar  
I am an Assistant Professor of Computer Science at Bilkent University, Ankara, Turkey. Previously, I was a senior research scientist at NVIDIA, Santa Clara, USA. I received my Ph.D. degree at Purdue University, under the supervision of Professor Eugenio Culurciello, in 2016. My research was focused on embedded vision systems and was featured in popular technology journals such as MIT Technology Review and BBC. I received a B.Sc. degree in Electrical and Electronics Engineering from Bogazici University in Turkey, in 2011. My current research focuses on deep learning algorithms for computer vision.

Recent Publications:

   Dual Contrastive Loss and Attention for GANs
Ning Yu, Guilin Liu, Aysegul Dundar, Andrew Tao, Bryan Catanzaro, Larry Davis, and Mario Fritz
ICCV 2021
   View Generalization for Single Image Textured 3D Models
Anand Bhattad, Aysegul Dundar, Guilin Liu, Andrew Tao, Bryan Catanzaro
CVPR 2021
Paper Web-page  
   Unsupervised Disentanglement of Pose, Appearance and Background from Images and Videos
Aysegul Dundar, Kevin J. Shih, Animesh Garg, Robert Pottorf, Andrew Tao, Bryan Catanzaro
T-PAMI 2021
Paper Github  
   Neural FFTs for Universal Texture Image Synthesis
Morteza Mardani, Guilin Liu, Aysegul Dundar, Shiqiu Liu, Andrew Tao, Bryan Catanzaro
NeurIPS 2020
   Panoptic-based Image Synthesis
Aysegul Dundar, Karan Sapra, Guilin Liu, Andrew Tao, Bryan Catanzaro
CVPR 2020
   Domain Stylization: A Fast Covariance Matching Framework towards Domain Adaptation
Aysegul Dundar, Ming-Yu Liu, Zhiding Yu, Ting-Chun Wang, John Zedlewski, Jan Kautz
T-PAMI 2020
   Unsupervised Video Interpolation Using Cycle Consistency
Fitsum A Reda, Deqing Sun, Aysegul Dundar, Mohammad Shoeybi, Guilin Liu, Kevin J Shih, Andrew Tao, Jan Kautz, Bryan Catanzaro
ICCV 2019
Paper Github  


  • Domain stylization using a neural network model. US Patent 10,984,286
  • Computing architecture with concurrent programmable data co-processor. US Patent 9,858,220
  • Video interpolation using one or more neural networks. US Patent App. 16/559,312
  • Video prediction using one or more neural networks. US Patent App. 16/558,620