Zobrazeno 1 - 10
of 290
pro vyhledávání: '"Lee Seungkyu"'
Autor:
Kim, Seunghwan, Lee, Seungkyu
Variational autoencoder (VAE) is an established generative model but is notorious for its blurriness. In this work, we investigate the blurry output problem of VAE and resolve it, exploiting the variance of Gaussian decoder and $\beta$ of beta-VAE. S
Externí odkaz:
http://arxiv.org/abs/2409.09361
Autor:
Yoon, Heechan, Lee, Seungkyu
Unlike opaque object, novel view synthesis of transparent object is a challenging task, because transparent object refracts light of background causing visual distortions on the transparent object surface along the viewpoint change. Recently introduc
Externí odkaz:
http://arxiv.org/abs/2312.08118
Autor:
Han, Dongshen, Lee, Seungkyu, Zhang, Chaoning, Yoon, Heechan, Kwon, Hyukmin, Kim, HyunCheol, Choo, HyonGon
Single Image Reflection Removal (SIRR) in real-world images is a challenging task due to diverse image degradations occurring on the glass surface during light transmission and reflection. Many existing methods rely on specific prior assumptions to r
Externí odkaz:
http://arxiv.org/abs/2312.03798
Autor:
Han, Dongshen, Lee, Seungkyu, Zhang, Chaoning, Yoon, Heechan, Kwon, Hyukmin, Kim, Hyun-Cheol, Choo, Hyon-Gon
Glass surfaces of transparent objects and mirrors are not able to be uniquely and explicitly characterized by their visual appearances because they contain the visual appearance of other reflected or transmitted surfaces as well. Detecting glass regi
Externí odkaz:
http://arxiv.org/abs/2307.00212
Autor:
Zhang, Chaoning, Han, Dongshen, Qiao, Yu, Kim, Jung Uk, Bae, Sung-Ho, Lee, Seungkyu, Hong, Choong Seon
Segment Anything Model (SAM) has attracted significant attention due to its impressive zero-shot transfer performance and high versatility for numerous vision applications (like image editing with fine-grained control). Many of such applications need
Externí odkaz:
http://arxiv.org/abs/2306.14289
Autor:
Han, Dongsheng, Zhang, Chaoning, Qiao, Yu, Qamar, Maryam, Jung, Yuna, Lee, SeungKyu, Bae, Sung-Ho, Hong, Choong Seon
Meta AI Research has recently released SAM (Segment Anything Model) which is trained on a large segmentation dataset of over 1 billion masks. As a foundation model in the field of computer vision, SAM (Segment Anything Model) has gained attention for
Externí odkaz:
http://arxiv.org/abs/2305.00278
Publikováno v:
In Annals of Nuclear Energy January 2025 210
Publikováno v:
In Case Studies in Thermal Engineering July 2024 59
Autor:
Kim, Sohee, Lee, Seungkyu
Continual learning is a concept of online learning with multiple sequential tasks. One of the critical barriers of continual learning is that a network should learn a new task keeping the knowledge of old tasks without access to any data of the old t
Externí odkaz:
http://arxiv.org/abs/2107.12657
Autor:
Kim, Sanghun, Lee, SeungKyu
Due to the unstable nature of minimax game between generator and discriminator, improving the performance of GANs is a challenging task. Recent studies have shown that selected high-quality samples in training improve the performance of GANs. However
Externí odkaz:
http://arxiv.org/abs/2107.11047