Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Kim, Kangyeol"'
Despite the growing prevalence of black-box pre-trained models (PTMs) such as prediction API services, there remains a significant challenge in directly applying general models to real-world scenarios due to the data distribution gap. Considering a d
Externí odkaz:
http://arxiv.org/abs/2408.07944
Autor:
Kim, Kangyeol, Seo, Wooseok, Nam, Sehyun, Kim, Bodam, Jeong, Suhyeon, Cho, Wonwoo, Choo, Jaegul, Yu, Youngjae
Personalized text-to-image (P-T2I) generation aims to create new, text-guided images featuring the personalized subject with a few reference images. However, balancing the trade-off relationship between prompt fidelity and identity preservation remai
Externí odkaz:
http://arxiv.org/abs/2407.09779
Accurately annotating multiple 3D objects in LiDAR scenes is laborious and challenging. While a few previous studies have attempted to leverage semi-automatic methods for cost-effective bounding box annotation, such methods have limitations in effici
Externí odkaz:
http://arxiv.org/abs/2312.15449
Recent remarkable improvements in large-scale text-to-image generative models have shown promising results in generating high-fidelity images. To further enhance editability and enable fine-grained generation, we introduce a multi-input-conditioned i
Externí odkaz:
http://arxiv.org/abs/2304.09748
Editing hairstyle is unique and challenging due to the complexity and delicacy of hairstyle. Although recent approaches significantly improved the hair details, these models often produce undesirable outputs when a pose of a source image is considera
Externí odkaz:
http://arxiv.org/abs/2208.07765
Autor:
Kim, Kangyeol, Park, Sunghyun, Lee, Junsoo, Lee, Joonseok, Kim, Sookyung, Choo, Jaegul, Choi, Edward
In order to perform unconditional video generation, we must learn the distribution of the real-world videos. In an effort to synthesize high-quality videos, various studies attempted to learn a mapping function between noise and videos, including rec
Externí odkaz:
http://arxiv.org/abs/2112.10960
We present a novel Animation CelebHeads dataset (AnimeCeleb) to address an animation head reenactment. Different from previous animation head datasets, we utilize 3D animation models as the controllable image samplers, which can provide a large amoun
Externí odkaz:
http://arxiv.org/abs/2111.07640
Autor:
Park, Sunghyun, Kim, Kangyeol, Lee, Junsoo, Choo, Jaegul, Lee, Joonseok, Kim, Sookyung, Choi, Edward
Video generation models often operate under the assumption of fixed frame rates, which leads to suboptimal performance when it comes to handling flexible frame rates (e.g., increasing the frame rate of the more dynamic portion of the video as well as
Externí odkaz:
http://arxiv.org/abs/2010.08188
Disentangling content and style information of an image has played an important role in recent success in image translation. In this setting, how to inject given style into an input image containing its own content is an important issue, but existing
Externí odkaz:
http://arxiv.org/abs/1911.13271