Jeong-Gi Kwak
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Jeong-Gi Kwak has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Hanseok Ko
Korea University
4 shared publications Dongsik Yoon
Korea University Seoul South Korea
3 shared publications- Yuanming Li
School of Electrical Engineering, Korea University, Seoul, South Korea
3 shared publications - David K. Han
Drexel University
2 shared publications - Youngsaeng Jin2 shared publications
- Bonhwa Ku
School of Electrical Engineering, Korea University, Seoul, South Korea
1 shared publication
Latest Publications
- Open Access
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Voost: A Unified and Scalable Diffusion Transformer for Bidirectional Virtual Try-On and Try-Off
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessVoost: A Unified and Scalable Diffusion Transformer for Bidirectional Virtual Try-On and Try-Off
- 3 March 2024
- Published by Elsevier in Pattern Recognition Letters
- Vol. 180, 68-74
Towards high-fidelity facial UV map generation in real-world
- 3 March 2024
- Published by Elsevier in Pattern Recognition Letters
- Vol. 180, 68-74
Towards high-fidelity facial UV map generation in real-world
- Open Access
Reference Guided Image Inpainting using Facial Attributes
Image inpainting is a technique of completing missing pixels such as occluded region restoration, distracting objects removal, and facial completion. Among these inpainting tasks, facial completion algorithm performs face inpainting according to the user direction. Existing approaches require delicate and well controlled input by the user, thus it is difficult for an average user to provide the guidance sufficiently accurate for the algorithm to generate desired results. To overcome this limitation, we propose an alternative user-guided inpainting architecture that manipulates facial attributes using a single reference image as the guide. Our end-to-end model consists of attribute extractors for accurate reference image attribute transfer and an inpainting model to map the attributes realistically and accurately to generated images. We customize MS-SSIM loss and learnable bidirectional attention maps in which importance structures remain intact even with irregular shaped masks. Based on our evaluation using the publicly available dataset CelebA-HQ, we demonstrate that the proposed method delivers superior performance compared to some state-of-the-art methods specialized in inpainting tasks.
Open AccessReference Guided Image Inpainting using Facial Attributes
Image inpainting is a technique of completing missing pixels such as occluded region restoration, distracting objects removal, and facial completion. Among these inpainting tasks, facial completion algorithm performs face inpainting according to the user direction. Existing approaches require delicate and well controlled input by the user, thus it is difficult for an average user to provide the guidance sufficiently accurate for the algorithm to generate desired results. To overcome this limitation, we propose an alternative user-guided inpainting architecture that manipulates facial attributes using a single reference image as the guide. Our end-to-end model consists of attribute extractors for accurate reference image attribute transfer and an inpainting model to map the attributes realistically and accurately to generated images. We customize MS-SSIM loss and learnable bidirectional attention maps in which importance structures remain intact even with irregular shaped masks. Based on our evaluation using the publicly available dataset CelebA-HQ, we demonstrate that the proposed method delivers superior performance compared to some state-of-the-art methods specialized in inpainting tasks.
- 24 October 2022
- Published by Springer Nature
- p. 236-253
Injecting 3D Perception of Controllable NeRF-GAN into StyleGAN for Editable Portrait Image Synthesis
- 24 October 2022
- Published by Springer Nature
- p. 236-253
Injecting 3D Perception of Controllable NeRF-GAN into StyleGAN for Editable Portrait Image Synthesis
- Open Access
Adverse Weather Image Translation with Asymmetric and Uncertainty-aware GAN
Adverse weather image translation belongs to the unsupervised image-to-image (I2I) translation task which aims to transfer adverse condition domain (eg, rainy night) to standard domain (eg, day). It is a challenging task because images from adverse domains have some artifacts and insufficient information. Recently, many studies employing Generative Adversarial Networks (GANs) have achieved notable success in I2I translation but there are still limitations in applying them to adverse weather enhancement. Symmetric architecture based on bidirectional cycle-consistency loss is adopted as a standard framework for unsupervised domain transfer methods. However, it can lead to inferior translation result if the two domains have imbalanced information. To address this issue, we propose a novel GAN model, i.e., AU-GAN, which has an asymmetric architecture for adverse domain translation. We insert a proposed feature transfer network (${T}$-net) in only a normal domain generator (i.e., rainy night-> day) to enhance encoded features of the adverse domain image. In addition, we introduce asymmetric feature matching for disentanglement of encoded features. Finally, we propose uncertainty-aware cycle-consistency loss to address the regional uncertainty of a cyclic reconstructed image. We demonstrate the effectiveness of our method by qualitative and quantitative comparisons with state-of-the-art models. Codes are available at https://github.com/jgkwak95/AU-GAN.
Open AccessAdverse Weather Image Translation with Asymmetric and Uncertainty-aware GAN
Adverse weather image translation belongs to the unsupervised image-to-image (I2I) translation task which aims to transfer adverse condition domain (eg, rainy night) to standard domain (eg, day). It is a challenging task because images from adverse domains have some artifacts and insufficient information. Recently, many studies employing Generative Adversarial Networks (GANs) have achieved notable success in I2I translation but there are still limitations in applying them to adverse weather enhancement. Symmetric architecture based on bidirectional cycle-consistency loss is adopted as a standard framework for unsupervised domain transfer methods. However, it can lead to inferior translation result if the two domains have imbalanced information. To address this issue, we propose a novel GAN model, i.e., AU-GAN, which has an asymmetric architecture for adverse domain translation. We insert a proposed feature transfer network (${T}$-net) in only a normal domain generator (i.e., rainy night-> day) to enhance encoded features of the adverse domain image. In addition, we introduce asymmetric feature matching for disentanglement of encoded features. Finally, we propose uncertainty-aware cycle-consistency loss to address the regional uncertainty of a cyclic reconstructed image. We demonstrate the effectiveness of our method by qualitative and quantitative comparisons with state-of-the-art models. Codes are available at https://github.com/jgkwak95/AU-GAN.