Search

Your search keyword '"Yang, Guo-Wei"' showing total 195 results
Start Over Author "Yang, Guo-Wei"
195 results on '"Yang, Guo-Wei"'

4. Recursive-NeRF: An Efficient and Dynamically Growing NeRF

Author

Yang, Guo-Wei, Zhou, Wen-Yang, Peng, Hao-Yang, Liang, Dun, Mu, Tai-Jiang, and Hu, Shi-Min

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

View synthesis methods using implicit continuous shape representations learned from a set of images, such as the Neural Radiance Field (NeRF) method, have gained increasing attention due to their high quality imagery and scalability to high resolution. However, the heavy computation required by its volumetric approach prevents NeRF from being useful in practice; minutes are taken to render a single image of a few megapixels. Now, an image of a scene can be rendered in a level-of-detail manner, so we posit that a complicated region of the scene should be represented by a large neural network while a small neural network is capable of encoding a simple region, enabling a balance between efficiency and quality. Recursive-NeRF is our embodiment of this idea, providing an efficient and adaptive rendering and training approach for NeRF. The core of Recursive-NeRF learns uncertainties for query coordinates, representing the quality of the predicted color and volumetric intensity at each level. Only query coordinates with high uncertainties are forwarded to the next level to a bigger neural network with a more powerful representational capability. The final rendered image is a composition of results from neural networks of all levels. Our evaluation on three public datasets shows that Recursive-NeRF is more efficient than NeRF while providing state-of-the-art quality. The code will be available at https://github.com/Gword/Recursive-NeRF., Comment: 11 pages, 12 figures

Published
2021

5. Growth, Electronic Structure and Superconductivity of Ultrathin Epitaxial CoSi2 Films

Author

Fang, Yuan, Wang, Ding, Li, Peng, Su, Hang, Le, Tian, Wu, Yi, Yang, Guo-Wei, Zhang, Hua-Li, Xiao, Zhi-Guang, Sun, Yan-Qiu, Hong, Si-Yuan, Xie, Yan-Wu, Wang, Huan-Hua, Cao, Chao, Lu, Xin, Yuan, Hui-Qiu, and Liu, Yang

Subjects
Condensed Matter - Mesoscale and Nanoscale Physics
Abstract

We report growth, electronic structure and superconductivity of ultrathin epitaxial CoSi2 films on Si(111). At low coverages, preferred islands with 2, 5 and 6 monolayers height develop, which agrees well with the surface energy calculation. We observe clear quantum well states as a result of electronic confinement and their dispersion agrees well with density functional theory calculations, indicating weak correlation effect despite strong contributions from Co 3d electrons. Ex-situ transport measurements show that superconductivity persists down to at least 10 monolayers, with reduced Tc but largely enhanced upper critical field. Our study opens up the opportunity to study the interplay between quantum confinement, interfacial symmetry breaking and superconductivity in an epitaxial silicide film, which is technologically relevant in microelectronics.

Published
2021

8. Weakly nonlinear incompressible Rayleigh–Taylor–Kelvin–Helmholtz instability in plane geometry.

Author

Zou, Zhen-Qi, Wu, Jun-Feng, Yang, Guo-Wei, Wang, Li-Feng, and Zhang, Wei-Yan

Subjects
RICHARDSON number, COMPUTER simulation
Abstract

A weakly nonlinear theoretical model is established for the two-dimensional incompressible Rayleigh–Taylor–Kelvin–Helmholtz instability (RT–KHI). The evolution of the perturbation interface is analytically studied by the third-order solution of the planar RT–KHI induced by a single-mode surface perturbation. The difference between the weakly nonlinear growth for Rayleigh–Taylor instability (RTI), Kelvin–Helmholtz instability (KHI), and RT–KHI in plane geometry is discussed. The trend of bubble and spike amplitudes with the Atwood number and the Richardson number is discussed in detail. The bubble and spike amplitudes of RT–KHI change from the KHI case to the RTI case as the Richardson number increases. The deflecting distance of bubble and spike vertices becomes smaller compared to the KHI case as the Richardson number increases. The dependence of the nonlinear saturation amplitude of RT–KHI on the Atwood number, the Richardson number, and the initial perturbation is obtained. The Richardson number is as vital to the nonlinear saturation amplitude as the Atwood number. It is found that the variation of the nonlinear saturation amplitude with the Atwood number at different Richardson numbers is divided into three parts, namely, "RTI-like part," "transition part," and "KHI-like part." In the transition part, the trend of the nonlinear saturation amplitude increasing with the Atwood number is completely opposite to the RTI and KHI cases. Finally, the theory is compared to the numerical simulation under identical initial conditions and displays good correspondence in the linear and weakly nonlinear stages. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

14. Multiple Convolutional Neural Network for Feature Extraction

Author

Yang, Guo-Wei, Jing, Hui-Fang, Hutchison, David, Series editor, Kanade, Takeo, Series editor, Kittler, Josef, Series editor, Kleinberg, Jon M., Series editor, Mattern, Friedemann, Series editor, Mitchell, John C., Series editor, Naor, Moni, Series editor, Pandu Rangan, C., Series editor, Steffen, Bernhard, Series editor, Terzopoulos, Demetri, Series editor, Tygar, Doug, Series editor, Weikum, Gerhard, Series editor, Huang, De-Shuang, editor, Jo, Kang-Hyun, editor, and Hussain, Abir, editor

Published
2015
Full Text
View/download PDF

17. Recursive-NeRF: An Efficient and Dynamically Growing NeRF

Author

Yang, Guo-Wei, Zhou, Wen-Yang, Peng, Hao-Yang, Liang, Dun, Mu, Tai-Jiang, and Hu, Shi-Min

Abstract

View synthesis methods using implicit continuous shape representations learned from a set of images, such as the Neural Radiance Field (NeRF) method, have gained increasing attention due to their high quality imagery and scalability to high resolution. However, the heavy computation required by its volumetric approach prevents NeRF from being useful in practice; minutes are taken to render a single image of a few megapixels. Now, an image of a scene can be rendered in a level-of-detail manner, so we posit that a complicated region of the scene should be represented by a large neural network while a small neural network is capable of encoding a simple region, enabling a balance between efficiency and quality. Recursive-NeRF is our embodiment of this idea, providing an efficient and adaptive rendering and training approach for NeRF. The core of Recursive-NeRF learns uncertainties for query coordinates, representing the quality of the predicted color and volumetric intensity at each level. Only query coordinates with high uncertainties are forwarded to the next level to a bigger neural network with a more powerful representational capability. The final rendered image is a composition of results from neural networks of all levels. Our evaluation on public datasets and a large-scale scene dataset we collected shows that Recursive-NeRF is more efficient than NeRF while providing state-of-the-art quality. The code will be available at https://github.com/Gword/Recursive-NeRF

Published
2023
Full Text
View/download PDF

19. Short-Text Classification Based on ICA and LSA

Author

Pu, Qiang, Yang, Guo-Wei, Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Dough, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Wang, Jun, editor, Yi, Zhang, editor, Zurada, Jacek M., editor, Lu, Bao-Liang, editor, and Yin, Hujun, editor

Published
2006
Full Text
View/download PDF

20. A New Adaptive Crossover Operator for the Preservation of Useful Schemata

Author

Li, Fan, Liu, Qi-He, Min, Fan, Yang, Guo-Wei, Hutchison, David, editor, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Naor, Moni, editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Dough, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Carbonell, Jaime G., editor, Siekmann, Jörg, editor, Yeung, Daniel S., editor, Liu, Zhi-Qiang, editor, Wang, Xi-Zhao, editor, and Yan, Hong, editor

Published
2006
Full Text
View/download PDF

21. Integrating New Cost Model into HMA-Based Grid Resource Scheduling

Author

Zhang, Jun-yan, Min, Fan, Yang, Guo-wei, Kanade, Takeo, editor, Kittler, Josef, editor, Kleinberg, Jon M., editor, Mattern, Friedemann, editor, Mitchell, John C., editor, Nierstrasz, Oscar, editor, Pandu Rangan, C., editor, Steffen, Bernhard, editor, Sudan, Madhu, editor, Terzopoulos, Demetri, editor, Tygar, Dough, editor, Vardi, Moshe Y., editor, Weikum, Gerhard, editor, Li, Minglu, editor, Sun, Xian-He, editor, Deng, Qianni, editor, and Ni, Jun, editor

Published
2004
Full Text
View/download PDF

29. Infrared/visible image feature domain fusion algorithm

Author

Wang Chuan-Yun, Yang Guo-Wei, and Sun Dong-Dong

Subjects
Image fusion, Fusion, Transformation (function), Computer science, Feature (computer vision), Computer Science::Computer Vision and Pattern Recognition, Principal component analysis, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Image segmentation, Algorithm, Image (mathematics), Domain (software engineering)
Abstract

Aiming at the community security and other fields which has strict requirements on the scale of infrared / visible image fusion calculation, this paper proposes an infrared / visible image feature domain fusion algorithm. The algorithm first uses the principal component analysis (PCA) model to transform the visible light image into the corresponding feature domain, and then projects the infrared light image onto the feature domain of the visible light image, and then performs segmented fusion of its principal components in the feature domain, and finally the fusion image is reconstructed. Experimental verification: when only 95% of the principal components are used for fusion, the performance of this algorithm in parameters such as STD and MI is better than some multi-scale transformation image fusion algorithms, and it is more excellent in the presentation of feature information.

Published
2021

34. Growth, electronic structure and superconductivity of ultrathin epitaxial CoSi2 films

Author

Fang, Yuan, primary, Wang, Ding, additional, Li, Peng, additional, Su, Hang, additional, Le, Tian, additional, Wu, Yi, additional, Yang, Guo-Wei, additional, Zhang, Hua-Li, additional, Xiao, Zhi-Guang, additional, Sun, Yan-Qiu, additional, Hong, Si-Yuan, additional, Xie, Yan-Wu, additional, Wang, Huan-Hua, additional, Cao, Chao, additional, Lu, Xin, additional, Yuan, Hui-Qiu, additional, and Liu, Yang, additional

Published
2021
Full Text
View/download PDF

40. Write-a-video

Author

Wang, Miao, primary, Yang, Guo-Wei, additional, Hu, Shi-Min, additional, Yau, Shing-Tung, additional, and Shamir, Ariel, additional

Published
2019
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results