no code implementations • 20 Nov 2024 • Bahri Batuhan Bilecen, Ahmet Berke Gokmen, Furkan Guzelant, Aysegul Dundar
3D head stylization transforms realistic facial features into artistic representations, enhancing user engagement across gaming and virtual reality applications.
no code implementations • 30 Sep 2024 • Bahri Batuhan Bilecen, Ahmet Berke Gokmen, Aysegul Dundar
Accompanying this, we propose a stitching framework on the triplane domain to get the best predictions from both.
1 code implementation • 13 Jun 2024 • Yigit Ekin, Ahmet Burak Yildirim, Erdem Eren Caglar, Aykut Erdem, Erkut Erdem, Aysegul Dundar
Advanced image editing techniques, particularly inpainting, are essential for seamlessly removing unwanted elements while preserving visual integrity.
no code implementations • 4 Apr 2024 • Bahri Batuhan Bilecen, Yigit Yalin, Ning Yu, Aysegul Dundar
Generative Adversarial Networks (GANs) have emerged as powerful tools for high-quality image generation and real image editing by manipulating their latent spaces.
no code implementations • 18 Dec 2023 • Ahmet Burak Yildirim, Hamza Pehlivan, Aysegul Dundar
However, their results either suffer from low fidelity to the input image or poor editing qualities, especially for edits that require large transformations.
1 code implementation • 25 Sep 2023 • Hakan Sivuk, Aysegul Dundar
Semantic image editing requires inpainting pixels following a semantic map.
no code implementations • ICCV 2023 • Ahmet Burak Yildirim, Hamza Pehlivan, Bahri Batuhan Bilecen, Aysegul Dundar
Specifically, we propose to learn an encoder and mixing network to combine encoded features from erased images with StyleGAN's mapped features from random samples.
no code implementations • 18 May 2023 • Aysegul Dundar, Jun Gao, Andrew Tao, Bryan Catanzaro
In this work, to overcome these limitations of generated datasets, we have two main contributions which lead us to achieve state-of-the-art results on challenging objects: 1) A robust multi-stage learning scheme that gradually relies more on the models own predictions when calculating losses, 2) A novel adversarial learning pipeline with online pseudo-ground truth generations to achieve fine details.
1 code implementation • 6 Apr 2023 • Ahmet Burak Yildirim, Vedat Baday, Erkut Erdem, Aykut Erdem, Aysegul Dundar
From the application point of view, a user needs to generate the masks for the objects they would like to remove which can be time-consuming and prone to errors.
1 code implementation • 6 Mar 2023 • Said Fahri Altindis, Adil Meric, Yusuf Dalva, Ugur Gudukbay, Aysegul Dundar
Estimating 3D human texture from a single image is essential in graphics and vision.
1 code implementation • CVPR 2023 • Hamza Pehlivan, Yusuf Dalva, Aysegul Dundar
We present a novel image inversion framework and a training pipeline to achieve high-fidelity image inversion with high-quality attribute editing.
no code implementations • 7 Jul 2022 • Yusuf Dalva, Said Fahri Altindis, Aysegul Dundar
However, while those models cannot be trained end-to-end and struggle to edit encoded images precisely, VecGAN is end-to-end trained for image translation task and successful at editing an attribute while preserving the others.
no code implementations • 17 Mar 2022 • Aysegul Dundar, Jun Gao, Andrew Tao, Bryan Catanzaro
The reconstruction is posed as an adaptation problem and is done progressively where in the first stage, we focus on learning accurate geometry, whereas in the second stage, we focus on learning the texture with a generative adversarial network.
no code implementations • 2 Sep 2021 • Said Fahri Altindis, Yusuf Dalva, Hamza Pehlivan, Aysegul Dundar
These presented robustness and generalization evaluations are important when designing instance segmentation models for real-world applications and picking an off-the-shelf pretrained model to directly use for the task at hand.
no code implementations • CVPR 2021 • Anand Bhattad, Aysegul Dundar, Guilin Liu, Andrew Tao, Bryan Catanzaro
We describe a cycle consistency loss that encourages model textures to be aligned, so as to encourage sharing.
1 code implementation • ICCV 2021 • Ning Yu, Guilin Liu, Aysegul Dundar, Andrew Tao, Bryan Catanzaro, Larry Davis, Mario Fritz
Lastly, we study different attention architectures in the discriminator, and propose a reference attention mechanism.
no code implementations • NeurIPS 2020 • Morteza Mardani, Guilin Liu, Aysegul Dundar, Shiqiu Liu, Andrew Tao, Bryan Catanzaro
The conventional CNNs, recently adopted for synthesis, require to train and test on the same set of images and fail to generalize to unseen images.
no code implementations • CVPR 2020 • Aysegul Dundar, Karan Sapra, Guilin Liu, Andrew Tao, Bryan Catanzaro
Conditional image synthesis for generating photorealistic images serves various applications for content editing to content generation.
1 code implementation • 26 Jan 2020 • Aysegul Dundar, Kevin J. Shih, Animesh Garg, Robert Pottorf, Andrew Tao, Bryan Catanzaro
However, the reconstruction task of the entire image forces the model to allocate landmarks to model the background.
no code implementations • 6 Sep 2019 • Kevin J. Shih, Aysegul Dundar, Animesh Garg, Robert Pottorf, Andrew Tao, Bryan Catanzaro
Prediction and interpolation for long-range video data involves the complex task of modeling motion trajectories for each visible object, occlusions and dis-occlusions, as well as appearance changes due to viewpoint and lighting.
1 code implementation • ICCV 2019 • Fitsum A. Reda, Deqing Sun, Aysegul Dundar, Mohammad Shoeybi, Guilin Liu, Kevin J. Shih, Andrew Tao, Jan Kautz, Bryan Catanzaro
We further introduce a pseudo supervised loss term that enforces the interpolated frames to be consistent with predictions of a pre-trained interpolation model.
Ranked #1 on
Video Frame Interpolation
on UCF101
(PSNR (sRGB) metric)
no code implementations • 24 Jul 2018 • Aysegul Dundar, Ming-Yu Liu, Ting-Chun Wang, John Zedlewski, Jan Kautz
Deep neural networks have largely failed to effectively utilize synthetic data when applied to real images due to the covariate shift problem.
no code implementations • 22 Nov 2017 • Aysegul Dundar, Ignacio Garcia-Dorado
Recent enhancements of deep convolutional neural networks (ConvNets) empowered by enormous amounts of labeled data have closed the gap with human performance for many object recognition tasks.
1 code implementation • 15 Jun 2017 • Ali Borji, Aysegul Dundar
We do not dwell much on the learning mechanisms in these frameworks as they are still a matter of debate, with respect to biological constraints.
no code implementations • 19 Nov 2015 • Aysegul Dundar, Jonghoon Jin, Eugenio Culurciello
In this work, we propose to train a deep convolutional network based on an enhanced version of the k-means clustering algorithm, which reduces the number of correlated parameters in the form of similar filters, and thus increases test categorization accuracy.
Ranked #49 on
Image Classification
on MNIST
no code implementations • 19 Nov 2015 • Jonghoon Jin, Aysegul Dundar, Eugenio Culurciello
Recent studies have shown that Convolutional Neural Networks (CNNs) are vulnerable to a small perturbation of input called "adversarial examples".
2 code implementations • 17 Dec 2014 • Jonghoon Jin, Aysegul Dundar, Eugenio Culurciello
We present flattened convolutional neural networks that are designed for fast feedforward execution.
1 code implementation • 1 Jun 2013 • Eugenio Culurciello, Jonghoon Jin, Aysegul Dundar, Jordan Bates
On the other hand, in unsupervised learning, one cannot rely on back-propagation techniques to learn the connections between layers.