Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Kwon, Youngjoong"'
Autor:
Kwon, Youngjoong, Fang, Baole, Lu, Yixing, Dong, Haoye, Zhang, Cheng, Carrasco, Francisco Vicente, Mosella-Montoro, Albert, Xu, Jianjin, Takagi, Shingo, Kim, Daeil, Prakash, Aayush, De la Torre, Fernando
Recent progress in neural rendering has brought forth pioneering methods, such as NeRF and Gaussian Splatting, which revolutionize view rendering across various domains like AR/VR, gaming, and content creation. While these methods excel at interpolat
Externí odkaz:
http://arxiv.org/abs/2407.12777
Generating controllable and photorealistic digital human avatars is a long-standing and important problem in Vision and Graphics. Recent methods have shown great progress in terms of either photorealism or inference speed while the combination of the
Externí odkaz:
http://arxiv.org/abs/2310.11449
We present a method that enables synthesizing novel views and novel poses of arbitrary human performers from sparse multi-view images. A key ingredient of our method is a hybrid appearance blending module that combines the advantages of the implicit
Externí odkaz:
http://arxiv.org/abs/2304.04897
Autor:
Wang, Shengze, Wang, Ziheng, Schmelzle, Ryan, Zheng, Liujie, Kwon, YoungJoong, Sengupta, Soumyadip, Fuchs, Henry
In this paper, we work to bring telepresence to every desktop. Unlike commercial systems, personal 3D video conferencing systems must render high-quality videos while remaining financially and computationally viable for the average consumer. To this
Externí odkaz:
http://arxiv.org/abs/2304.01197
Autor:
Wang, Shengze, Kwon, YoungJoong, Shen, Yuan, Zhang, Qian, State, Andrei, Huang, Jia-Bin, Fuchs, Henry
There have been significant advancements in dynamic novel view synthesis in recent years. However, current deep learning models often require (1) prior models (e.g., SMPL human models), (2) heavy pre-processing, or (3) per-scene optimization. We prop
Externí odkaz:
http://arxiv.org/abs/2204.10477
In this paper, we aim at synthesizing a free-viewpoint video of an arbitrary human performance using sparse multi-view cameras. Recently, several works have addressed this problem by learning person-specific neural radiance fields (NeRF) to capture t
Externí odkaz:
http://arxiv.org/abs/2109.07448
Autor:
Seo, Bo-Bae, Kwon, Youngjoong, Kim, Jun, Hong, Ki Hyun, Kim, Sung-Eun, Song, Hae-Ryong, Kim, Young-Min, Song, Soo-Chang
Publikováno v:
In Bioactive Materials January 2022 7:14-25
Autor:
Seo, Bo-Bae, Kwon, Youngjoong, Kim, Jun, Hong, Ki Hyun, Kim, Sung-Eun, Song, Hae-Ryong, Kim, Young-Min, Song, Soo-Chang
Publikováno v:
Bioactive Materials; 20210101, Issue: Preprints
Publikováno v:
IEEE transactions on visualization and computer graphics [IEEE Trans Vis Comput Graph] 2024 Jun 14; Vol. PP. Date of Electronic Publication: 2024 Jun 14.