1 code implementation • IEEE Access 2023 • Levent Karacan
The proposed model comprises an encoder-decoder network, and a trainable self-guided filtering (TSGF) module that is specifically designed to enhance spatial consistency in the predicted focus map and to eliminate the requirements of post-processing in existing GAN-based methods.
1 code implementation • Signal Processing: Image Communication 2023 • Levent Karacan
We develop a Multi-image Transformer (MiT) for MFIF by being inspired by a Spatial-Temporal Transformer Network (STTN) so that global connection can be modeled along multiple input images.
1 code implementation • Pattern Recognition Letters 2023 • Mehmet SARIGÜL, Levent Karacan
The proposed approach maps image features from different camera views of the same 3D region to nearby points in the learned feature space.
no code implementations • ICCV 2023 • Moayed Haji Ali, Andrew Bond, Tolga Birdal, Duygu Ceylan, Levent Karacan, Erkut Erdem, Aykut Erdem
However, the applicability of such advancements to the video domain has been hindered by the difficulty of representing and controlling videos in the latent space of GANs.
1 code implementation • 5 Nov 2022 • Levent Karacan, Tolga Kerimoğlu, İsmail İnan, Tolga Birdal, Erkut Erdem, Aykut Erdem
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 problems in computer vision.
no code implementations • 22 Aug 2018 • Levent Karacan, Zeynep Akata, Aykut Erdem, Erkut Erdem
In this study, we explore building a two-stage framework for enabling users to directly manipulate high-level attributes of a natural scene.
2 code implementations • 5 Feb 2018 • Salman Ul Hassan Dar, Mahmut Yurt, Levent Karacan, Aykut Erdem, Erkut Erdem, Tolga Çukur
The proposed approach preserves high-frequency details via an adversarial loss; and it offers enhanced synthesis performance via a pixel-wise loss for registered multi-contrast images and a cycle-consistency loss for unregistered images.
no code implementations • 1 Dec 2016 • Levent Karacan, Zeynep Akata, Aykut Erdem, Erkut Erdem
Automatic image synthesis research has been rapidly growing with deep networks getting more and more expressive.
no code implementations • ICCV 2015 • Levent Karacan, Aykut Erdem, Erkut Erdem
Previous sampling-based image matting methods typically rely on certain heuristics in collecting representative samples from known regions, and thus their performance deteriorates if the underlying assumptions are not satisfied.