Search Results - "Choi, Yunjey"

Rethinking the Truly Unsupervised Image-to-Image Translation by Baek, Kyungjune, Choi, Yunjey, Uh, Youngjung, Yoo, Jaejun, Shim, Hyunjung

“…Every recent image-to-image translation model inherently requires either image-level (i.e. input-output pairs) or set-level (i.e. domain labels) supervision…”
Get full text

StarGAN v2: Diverse Image Synthesis for Multiple Domains by Choi, Yunjey, Uh, Youngjung, Yoo, Jaejun, Ha, Jung-Woo

“…A good image-to-image translation model should learn a mapping between different visual domains while satisfying the following properties: 1) diversity of…”
Get full text

StarGAN: Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation by Choi, Yunjey, Choi, Minje, Kim, Munyoung, Ha, Jung-Woo, Kim, Sunghun, Choo, Jaegul

“…Recent studies have shown remarkable success in image-to-image translation for two domains. However, existing approaches have limited scalability and…”
Get full text

Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing by Kim, Hyunsu, Choi, Yunjey, Kim, Junho, Yoo, Sungjoo, Uh, Youngjung

“…Generative adversarial networks (GANs) synthesize realistic images from random latent vectors. Although manipulating the latent vectors controls the…”
Get full text

Feature Statistics Mixing Regularization for Generative Adversarial Networks by Kim, Junho, Choi, Yunjey, Uh, Youngjung

“…In generative adversarial networks, improving discriminators is one of the key components for generation performance. As image classifiers are biased toward…”
Get full text

Diffusion Video Autoencoders: Toward Temporally Consistent Face Video Editing via Disentangled Video Encoding by Kim, Gyeongman, Shim, Hajin, Kim, Hyunsu, Choi, Yunjey, Kim, Junho, Yang, Eunho

“…Inspired by the impressive performance of recent face image editing methods, several studies have been naturally proposed to extend these methods to the face…”
Get full text

Visual Style Prompting with Swapping Self-Attention by Jeong, Jaeseok, Kim, Junho, Choi, Yunjey, Lee, Gayoung, Uh, Youngjung

“…In the evolving domain of text-to-image generation, diffusion models have emerged as powerful tools in content creation. Despite their remarkable capability,…”
Get full text

Feature Statistics Mixing Regularization for Generative Adversarial Networks by Kim, Junho, Choi, Yunjey, Uh, Youngjung

“…In generative adversarial networks, improving discriminators is one of the key components for generation performance. As image classifiers are biased toward…”
Get full text

Custom-Edit: Text-Guided Image Editing with Customized Diffusion Models by Choi, Jooyoung, Choi, Yunjey, Kim, Yunji, Kim, Junho, Yoon, Sungroh

“…Text-to-image diffusion models can generate diverse, high-fidelity images based on user-provided text prompts. Recent research has extended these models to…”
Get full text

Learning Input-agnostic Manipulation Directions in StyleGAN with Text Guidance by Kim, Yoonjeon, Kim, Hyunsu, Kim, Junho, Choi, Yunjey, Yang, Eunho

“…With the advantages of fast inference and human-friendly flexible manipulation, image-agnostic style manipulation via text guidance enables new applications…”
Get full text

Memory Efficient Patch-based Training for INR-based GANs by Lee, Namwoo, Kim, Hyunsu, Lee, Gayoung, Yoo, Sungjoo, Choi, Yunjey

“…Recent studies have shown remarkable progress in GANs based on implicit neural representation (INR) - an MLP that produces an RGB value given its (x, y)…”
Get full text

User-friendly Image Editing with Minimal Text Input: Leveraging Captioning and Injection Techniques by Kim, Sunwoo, Jang, Wooseok, Kim, Hyunsu, Kim, Junho, Choi, Yunjey, Kim, Seungryong, Lee, Gayeong

“…Recent text-driven image editing in diffusion models has shown remarkable success. However, the existing methods assume that the user's description…”
Get full text

3D-aware Blending with Generative NeRFs by Kim, Hyunsu, Lee, Gayoung, Choi, Yunjey, Kim, Jin-Hwa, Zhu, Jun-Yan

“…Image blending aims to combine multiple images seamlessly. It remains challenging for existing 2D-based methods, especially when input images are misaligned…”
Get full text

Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing by Kim, Hyunsu, Choi, Yunjey, Kim, Junho, Yoo, Sungjoo, Uh, Youngjung

“…Generative adversarial networks (GANs) synthesize realistic images from random latent vectors. Although manipulating the latent vectors controls the…”
Get full text

Diffusion Video Autoencoders: Toward Temporally Consistent Face Video Editing via Disentangled Video Encoding by Kim, Gyeongman, Shim, Hajin, Kim, Hyunsu, Choi, Yunjey, Kim, Junho, Yang, Eunho

“…Inspired by the impressive performance of recent face image editing methods, several studies have been naturally proposed to extend these methods to the face…”
Get full text

Generator Knows What Discriminator Should Learn in Unconditional GANs by Lee, Gayoung, Kim, Hyunsu, Kim, Junho, Kim, Seonghyeon, Ha, Jung-Woo, Choi, Yunjey

“…Recent methods for conditional image generation benefit from dense supervision such as segmentation label maps to achieve high-fidelity. However, it is rarely…”
Get full text

Rarity Score : A New Metric to Evaluate the Uncommonness of Synthesized Images by Han, Jiyeon, Choi, Hwanil, Choi, Yunjey, Kim, Junho, Ha, Jung-Woo, Choi, Jaesik

“…Evaluation metrics in image synthesis play a key role to measure performances of generative models. However, most metrics mainly focus on image fidelity…”
Get full text

Rethinking the Truly Unsupervised Image-to-Image Translation by Baek, Kyungjune, Choi, Yunjey, Uh, Youngjung, Yoo, Jaejun, Shim, Hyunjung

“…Every recent image-to-image translation model inherently requires either image-level (i.e. input-output pairs) or set-level (i.e. domain labels) supervision…”
Get full text

StarGAN v2: Diverse Image Synthesis for Multiple Domains by Choi, Yunjey, Uh, Youngjung, Yoo, Jaejun, Ha, Jung-Woo

“…A good image-to-image translation model should learn a mapping between different visual domains while satisfying the following properties: 1) diversity of…”
Get full text

Reliable Fidelity and Diversity Metrics for Generative Models by Naeem, Muhammad Ferjad, Oh, Seong Joon, Uh, Youngjung, Choi, Yunjey, Yoo, Jaejun

“…Devising indicative evaluation metrics for the image generation task remains an open problem. The most widely used metric for measuring the similarity between…”
Get full text