Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Shih-En Wei"'
Autor:
Shih-En Wei, 魏士恩
100
Clustering of machines for better spatial reuse has been considered as one key technology for supporting machine-to-machine (M2M) communications with a large number of communicating devices. Most related work, however, focuses on developing
Clustering of machines for better spatial reuse has been considered as one key technology for supporting machine-to-machine (M2M) communications with a large number of communicating devices. Most related work, however, focuses on developing
Externí odkaz:
http://ndltd.ncl.edu.tw/handle/52020030383902082855
Autor:
Chen Cao, Tomas Simon, Jin Kyu Kim, Gabe Schwartz, Michael Zollhoefer, Shun-Suke Saito, Stephen Lombardi, Shih-En Wei, Danielle Belko, Shoou-I Yu, Yaser Sheikh, Jason Saragih
Publikováno v:
ACM Transactions on Graphics. 41:1-19
Creating photorealistic avatars of existing people currently requires extensive person-specific data capture, which is usually only accessible to the VFX industry and not the general public. Our work aims to address this drawback by relying only on a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0a53614823649af8c5177ea058e7a083
https://doi.org/10.1145/3528223.3530143
https://doi.org/10.1145/3528223.3530143
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 43:3681-3694
We present Supervision by Registration and Triangulation (SRT), an unsupervised approach that utilizes unlabeled multi-view video to improve the accuracy and precision of landmark detectors. Being able to utilize unlabeled data enables our detectors
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4b88006e53936723d97a5112d79b19b0
https://doi.org/10.1109/tpami.2020.2983935
https://doi.org/10.1109/tpami.2020.2983935
Autor:
Kevyn Mcphail, Sai Bi, Tomas Simon, Yaser Sheikh, Ravi Ramamoorthi, Stephen Lombardi, Shunsuke Saito, Jason Saragih, Shih-En Wei
Publikováno v:
ACM Transactions on Graphics. 40:1-15
We present a method for building high-fidelity animatable 3D face models that can be posed and rendered with novel lighting environments in real-time. Our main insight is that relightable models trained to produce an image lit from a single light dir
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5a095e5f4579fc337188241cb50ce797
https://doi.org/10.1145/3450626.3459829
https://doi.org/10.1145/3450626.3459829
Autor:
Amin Jourabloo, Fernando De La Torre, Jason Saragih, Shih-En Wei, Stephen Lombardi, Te-Li Wang, Danielle Belko, Autumn Trimble, Hernan Badino
Publikováno v:
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3dabafffb9d3c489019e13baab5ac360
https://doi.org/10.1109/cvpr52688.2022.01968
https://doi.org/10.1109/cvpr52688.2022.01968
Autor:
Tomas Simon, Hypes Alexander Trenor, Yaser Sheikh, Shih-En Wei, Hernan Badino, Adam W. Harley, Stephen Lombardi, Dawei Wang, Jason Saragih, Michal Perdoch
Publikováno v:
ACM Transactions on Graphics. 38:1-16
A key promise of Virtual Reality (VR) is the possibility of remote social interaction that is more immersive than any prior telecommunication media. However, existing social VR experiences are mediated by inauthentic digital representations of the us
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::695518f352d253534d450789bdeac27b
https://doi.org/10.1145/3306346.3323030
https://doi.org/10.1145/3306346.3323030
Autor:
Yaser Sheikh, Weipeng Xu, Tomas Simon, Fabian Prada, Takaaki Shiratori, Chenglei Wu, Jason Saragih, Timur Bagautdinov, Shih-En Wei
We present a learning-based method for building driving-signal aware full-body avatars. Our model is a conditional variational autoencoder that can be animated with incomplete driving signals, such as human pose and facial keypoints, and produces a h
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ff93f91f3bf052125b4f00592f3f0d87
http://arxiv.org/abs/2105.10441
http://arxiv.org/abs/2105.10441
Publikováno v:
CVPR
Accurate estimation of 3D human motion from monocular video requires modeling both kinematics (body motion without physical forces) and dynamics (motion with physical forces). To demonstrate this, we present SimPoE, a Simulation-based approach for 3D
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a946ec1cb1d5282df29d5dbf1db6fd04
Autor:
Jason Saragih, Shih-En Wei, Te-Li Wang, Gabriel Schwartz, Stephen Lombardi, Yaser Sheikh, Tomas Simon
Publikováno v:
ACM Transactions on Graphics. 39
Interacting with people across large distances is important for remote work, interpersonal relationships, and entertainment. While such face-to-face interactions can be achieved using 2D video conferencing or, more recently, virtual reality (VR), tel
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bcf3b0a19c271330a44699926166baca
https://doi.org/10.1145/3386569.3392493
https://doi.org/10.1145/3386569.3392493
Image Disentanglement and Uncooperative Re-Entanglement for High-Fidelity Image-to-Image Translation
Publikováno v:
ICCV Workshops
Cross-domain image-to-image translation should satisfy two requirements: (1) preserve the information that is common to both domains, and (2) generate convincing images covering variations that appear in the target domain. This is challenging, especi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b8bfec14e8a69e94d5d96e82022a5c4d