3 papers
cs.CV2022
Disentangling Content and Motion for Text-Based Neural Video Manipulation
Levent Karacan, Tolga Kerimoğlu, İsmail İnan +3
Giving machines the ability to imagine possible new objects or scenes from linguistic descriptions and produce their realistic renderings is arguably one of the most challenging pr…
cs.CV2018
Manipulating Attributes of Natural Scenes via Hallucination
Levent Karacan, Zeynep Akata, Aykut Erdem +1
In this study, we explore building a two-stage framework for enabling users to directly manipulate high-level attributes of a natural scene. The key to our approach is a deep gener…
cs.CV2018
Image Synthesis in Multi-Contrast MRI with Conditional Generative Adversarial Networks
Salman Ul Hassan Dar, Mahmut Yurt, Levent Karacan +3
Acquiring images of the same anatomy with multiple different contrasts increases the diversity of diagnostic information available in an MR exam. Yet, scan time limitations may pro…