no code implementations • 24 Jan 2024 • Yuanming Li, Gwantae Kim, Jeong-gi Kwak, Bon-hwa Ku, Hanseok Ko
Finally, we fine-tuned a pre-trained face landmark detection model on the synthetic dataset to achieve multi-domain face landmark detection.
no code implementations • 3 Dec 2023 • Jeong-gi Kwak, Erqun Dong, Yuhe Jin, Hanseok Ko, Shweta Mahajan, Kwang Moo Yi
Thus, to perform novel-view synthesis, we create a smooth camera trajectory to the target view that we wish to render, and denoise using both a view-conditioned diffusion model and a video diffusion model.
no code implementations • 20 Jan 2023 • Dongsik Yoon, Jeong-gi Kwak, Yuanming Li, David Han, Hanseok Ko
Image inpainting is an old problem in computer vision that restores occluded regions and completes damaged images.
no code implementations • 24 Sep 2022 • Yuanming Li, Jeong-gi Kwak, David Han, Hanseok Ko
Our model relies on pretrained StyleGAN, and the proposed model is trained in a self-supervised manner without any manual annotations or datasets.
1 code implementation • 21 Jul 2022 • Jeong-gi Kwak, Yuanming Li, Dongsik Yoon, Donghyeon Kim, David Han, Hanseok Ko
To alleviate the issue, many 3D-aware GANs have been proposed and shown notable results, but 3D GANs struggle with editing semantic attributes.
no code implementations • 6 May 2022 • Jeong-gi Kwak, Yuanming Li, Dongsik Yoon, David Han, Hanseok Ko
Although the progress of generative models enables the stylization of a portrait, obtaining the stylized image in canonical view is still a challenging task.
no code implementations • 3 May 2022 • Donghyeon Kim, Gwantae Kim, Bokyeung Lee, Jeong-gi Kwak, David K. Han, Hanseok Ko
However, the performance of the dynamic filter might be degraded since simple feature pooling is used to reduce the computational resource in the IDF part.
1 code implementation • 8 Dec 2021 • Jeong-gi Kwak, Youngsaeng Jin, Yuanming Li, Dongsik Yoon, Donghyeon Kim, Hanseok Ko
To address this issue, we propose a novel GAN model, i. e., AU-GAN, which has an asymmetric architecture for adverse domain translation.
1 code implementation • ECCV 2020 • Jeong-gi Kwak, David K. Han, Hanseok Ko
The goal of face attribute editing is altering a facial image according to given target attributes such as hair color, mustache, gender, etc.