Zobrazeno 1 - 10
of 14
pro vyhledávání: '"Donglai Xiang"'
Autor:
Oshri Halimi, Tuur Stuyck, Donglai Xiang, Timur Bagautdinov, He Wen, Ron Kimmel, Takaaki Shiratori, Chenglei Wu, Yaser Sheikh, Fabian Prada
Publikováno v:
ACM Transactions on Graphics. 41:1-17
We propose a novel multi-view camera pipeline for the reconstruction and registration of dynamic clothing. Our proposed method relies on a specifically designed pattern that allows for precise video tracking in each camera view. We triangulate the tr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d3ea0d47718fd9197223dc4c497750fb
https://doi.org/10.1145/3550454.3555448
https://doi.org/10.1145/3550454.3555448
We propose a novel sparse constrained formulation and from it derive a real-time optimization method for 3D human pose and shape estimation. Our optimization method, SCOPE (Sparse Constrained Optimization for 3D human Pose and shapE estimation), is o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c41f5ac53ceace9831e20495a8238dec
Autor:
He Wen, Timur Bagautdinov, Donglai Xiang, Chenglei Wu, Weipeng Xu, Fabian Prada, Yuan Dong, Jessica K. Hodgins
We have recently seen great progress in building photorealistic animatable full-body codec avatars, but generating high-fidelity animation of clothing is still difficult. To address these difficulties, we propose a method to build an animatable cloth
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a084b57b9c33a01524d3cfebfa9a6dde
Publikováno v:
3DV
We present a method to capture temporally coherent dynamic clothing deformation from a monocular RGB video input. In contrast to the existing literature, our method does not require a pre-scanned personalized mesh template, and thus can be applied to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8c6121e371a520e3ec8e67f493b1be1c
http://arxiv.org/abs/2009.10711
http://arxiv.org/abs/2009.10711
Publikováno v:
Journal of Biomechanics. 129:110650
The field of biomechanics is at a turning point, with marker-based motion capture set to be replaced by portable and inexpensive hardware, rapidly improving markerless tracking algorithms, and open datasets that will turn these new technologies into
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e2c8efdda03167d818ddc177413fee30
https://doi.org/10.1016/j.jbiomech.2021.110650
https://doi.org/10.1016/j.jbiomech.2021.110650
Autor:
Donglai Xiang, Gines Hidalgo Martinez, Yaadhav Raaj, Haroon Idrees, Tomas Simon, Yaser Sheikh, Hanbyul Joo
Publikováno v:
ICCV
We present the first single-network approach for 2D~whole-body pose estimation, which entails simultaneous localization of body, face, hands, and feet keypoints. Due to the bottom-up formulation, our method maintains constant real-time performance re
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9fda9d35384b2a2124ff2ac5d2e9916d
http://arxiv.org/abs/1909.13423
http://arxiv.org/abs/1909.13423
Publikováno v:
CVPR
The body pose of a person wearing a camera is of great interest for applications in augmented reality, healthcare, and robotics, yet much of the person's body is out of view for a typical wearable camera. We propose a learning-based approach to estim
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::34eaa3ad79f1d20c884da40bfad843c7
Publikováno v:
CVPR
We present the first method to capture the 3D total motion of a target person from a monocular view input. Given an image or a monocular video, our method reconstructs the motion from body, face, and fingers represented by a 3D deformable mesh model.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8e22ee021038a569e7a8a44b857780f0
Publikováno v:
ICDAR
This paper investigates local discriminant training and global optimization methods for Convolutional Neural Network (CNN) to improve its discriminant ability and recognition accuracy. For local discriminant training, we propose to combine triplet lo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5ee37800f18ed57c0afc404b4b9e9581
https://doi.org/10.1109/icdar.2017.70
https://doi.org/10.1109/icdar.2017.70
Publikováno v:
ICCV
We study the problem of single-image depth estimation for images in the wild. We collect human annotated surface normals and use them to help train a neural network that directly predicts pixel-wise depth. We propose two novel loss functions for trai
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a43cdd4c25093cede6a6777b4a41df5e
https://doi.org/10.1109/iccv.2017.173
https://doi.org/10.1109/iccv.2017.173