Подписаться
Mingi Kwon
Mingi Kwon
Подтвержден адрес электронной почты в домене yonsei.ac.kr - Главная страница
Название
Процитировано
Процитировано
Год
Diffusion models already have a semantic latent space
M Kwon, J Jeong, Y Uh
arXiv preprint arXiv:2210.10960, 2022
2202022
Understanding the latent space of diffusion models through the lens of riemannian geometry
YH Park, M Kwon, J Choi, J Jo, Y Uh
Advances in Neural Information Processing Systems 36, 24129-24142, 2023
442023
Training-free Content Injection using h-space in Diffusion Models
J Jeong, M Kwon, Y Uh
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer …, 2024
34*2024
Unsupervised discovery of semantic latent directions in diffusion models
YH Park, M Kwon, J Jo, Y Uh
arXiv preprint arXiv:2302.12469, 2023
212023
Customize-a-video: One-shot motion customization of text-to-video diffusion models
Y Ren, Y Zhou, J Yang, J Shi, D Liu, F Liu, M Kwon, A Shrivastava
arXiv preprint arXiv:2402.14780, 2024
192024
Furrygan: High quality foreground-aware image synthesis
J Bae, M Kwon, Y Uh
European Conference on Computer Vision, 696-712, 2022
52022
Plug-and-Play Diffusion Distillation
YT Hsiao, S Khodadadeh, K Duarte, WA Lin, H Qu, M Kwon, R Kalarot
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2024
42024
Harivo: Harnessing text-to-image models for video generation
M Kwon, SW Oh, Y Zhou, D Liu, JY Lee, H Cai, B Liu, F Liu, Y Uh
European Conference on Computer Vision, 19-36, 2025
22025
Attribute Based Interpretable Evaluation Metrics for Generative Models
D Kim, M Kwon, Y Uh
arXiv preprint arXiv:2310.17261, 2023
22023
Customize-A-Video: One-Shot Motion Customization of Text-to-Video Diffusion Models
F Liu, M Kwon, A Shrivastava
В данный момент система не может выполнить эту операцию. Повторите попытку позднее.
Статьи 1–10