Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Zhenglin Geng"'
Publikováno v:
Special Interest Group on Computer Graphics and Interactive Techniques Conference Proceedings.
We present a novel paradigm for modeling certain types of dynamic simulation in real-time with the aid of neural networks. In order to significantly reduce the requirements on data (especially time-dependent data), as well as decrease generalization
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f9348a4ff93b1ce188db178da64baaef
https://doi.org/10.1145/3528233.3530705
https://doi.org/10.1145/3528233.3530705
Publikováno v:
Computer Graphics Forum. 39:135-144
We propose a novel approach to learning cloth deformation as a function of body pose, recasting the graph-like triangle mesh data structure into image-based data in order to leverage popular and well-developed convolutional neural networks (CNNs) in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3b4eed75cd19b1fe35121a63ef9f42e9
https://doi.org/10.1111/cgf.14108
https://doi.org/10.1111/cgf.14108
Publikováno v:
International Journal of Computer Vision. 128:2744-2761
We present a method for photo-realistic face manipulation. Given a single RGB face image with an arbitrary expression, our method can synthesize another arbitrary expression of the same person. To achieve this, we first fit a 3D face model and disent
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::150f1380cafc1b736e1b2148dc8c99ce
https://doi.org/10.1007/s11263-020-01361-8
https://doi.org/10.1007/s11263-020-01361-8
Publikováno v:
Journal of Physics: Conference Series. 2278:012005
In order to solve the problems of ant colony algorithm in the path planning of mobile robots, such as slow convergence speed and easy to fall into local optimum, an improved algorithm of adaptive ant colony algorithm is proposed in this paper. The al
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::05b57c5a3a1754c7e00f36c98ba46561
https://doi.org/10.1088/1742-6596/2278/1/012005
https://doi.org/10.1088/1742-6596/2278/1/012005
Regularization is used to avoid overfitting when training a neural network; unfortunately, this reduces the attainable level of detail hindering the ability to capture high-frequency information present in the training data. Even though various appro
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bbd3769f437f07caa6629f2b264c51e3
http://arxiv.org/abs/2001.07253
http://arxiv.org/abs/2001.07253
Publikováno v:
CVPR
We present a method for fine-grained face manipulation. Given a face image with an arbitrary expression, our method can synthesize another arbitrary expression by the same person. This is achieved by first fitting a 3D face model and then disentangli
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::27927bfe0e23fa4f236069656e6df528
https://doi.org/10.1109/cvpr.2019.01005
https://doi.org/10.1109/cvpr.2019.01005
Publikováno v:
Journal of Computational Physics. 406:109099
Many machine/deep learning artificial neural networks are trained to simply be interpolation functions that map input variables to output values interpolated from the training data in a linear/nonlinear fashion. Even when the input/output pairs of th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b06363717572ec681d2d3f497b584f74
https://doi.org/10.1016/j.jcp.2019.109099
https://doi.org/10.1016/j.jcp.2019.109099
Publikováno v:
Lecture Notes in Electrical Engineering ISBN: 9789811300288
GNSS spoofing signals have the same signal structure as authentic signals, so it is difficult to mitigate the spoofing in time and frequency domains, and space domain processing has become one of the most powerful methods for spoofing cancelation. Bu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::85892e817d61de77a67b518d471b0fda
https://doi.org/10.1007/978-981-13-0029-5_37
https://doi.org/10.1007/978-981-13-0029-5_37
Publikováno v:
Proceedings of the ACM SIGGRAPH / Eurographics Symposium on Computer Animation.
As has been noted and discussed by various authors, numerical simulations of deformable bodies often adversely suffer from so-called "locking" artifacts. We illustrate that the "locking" of out-of-plane bending motion that results from even an edge-s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f2945c903af73b417fdd81210c003842
https://doi.org/10.1145/3099564.3099568
https://doi.org/10.1145/3099564.3099568