Zobrazeno 1 - 10
of 38
pro vyhledávání: '"Sung-Fang Tsai"'
Autor:
Sung-Fang Tsai, 蔡松芳
101
Video is increasingly used in a wide variety of applications. In the future, more than 90% of internet traffic will be video in 2014. While the bandwidth-consuming video is more and more used, resolution requirement on the other hand is goin
Video is increasingly used in a wide variety of applications. In the future, more than 90% of internet traffic will be video in 2014. While the bandwidth-consuming video is more and more used, resolution requirement on the other hand is goin
Externí odkaz:
http://ndltd.ncl.edu.tw/handle/93497571279831785882
Autor:
Sung-Fang Tsai, 蔡松芳
95
Motion estimation provides and efficient encoding tools, but it also occupy a lot of computing power. In high definition video application, the problem would be more serious. A reconfigurable motion estimation with power scalability is propos
Motion estimation provides and efficient encoding tools, but it also occupy a lot of computing power. In high definition video application, the problem would be more serious. A reconfigurable motion estimation with power scalability is propos
Externí odkaz:
http://ndltd.ncl.edu.tw/handle/14455387050389361948
Autor:
Wei-Sheng Lai, Yichang Shih, Lun-Cheng Chu, Xiaotong Wu, Sung-Fang Tsai, Michael Krainin, Deqing Sun, Chia-Kai Liang
Motion blur of fast-moving subjects is a longstanding problem in photography and very common on mobile phones due to limited light collection efficiency, particularly in low-light conditions. While we have witnessed great progress in image deblurring
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1c121416b39590bb0bbae669348c388a
http://arxiv.org/abs/2207.11617
http://arxiv.org/abs/2207.11617
Publikováno v:
ICIP
We present Steadiface, a new real-time face-centric video stabilization method that simultaneously removes hand shake and keeps subject's head stable. We use a CNN to estimate the face landmarks and use them to optimize a stabilized head center. We t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e3e89e9757db04e89ee298cb2e635aba
http://arxiv.org/abs/1905.01382
http://arxiv.org/abs/1905.01382
Publikováno v:
ICIP
We present an algorithm for real-time video denoising on mobile platforms. Based on Gaussian-Laplacian pyramid decomposition, our solution's main contributions are fast alignment and a new interpolation function that fuses noisy frames into a denoise
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c591513d1d7aa09854a1916ed66af464
https://doi.org/10.1109/icip.2018.8451416
https://doi.org/10.1109/icip.2018.8451416
Autor:
Chien Wu, Tung-Chien Chen, Yen-Chieh Lai, Liang-Gee Chen, Shao-Yi Chien, Sung-Fang Tsai, Chung-Te Li
Publikováno v:
IEEE Transactions on Circuits and Systems for Video Technology. 23:1137-1149
2-D-to-3-D conversion is an important step for obtaining 3-D videos, as a variety of monocular depth cues have been explored to generate 3-D videos from 2-D videos. As in a human brain, a fusion of these monocular depth cues can regenerate 3-D data f
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::285fac7df0fe3ec8069de6bbfd25744b
https://doi.org/10.1109/tcsvt.2012.2223874
https://doi.org/10.1109/tcsvt.2012.2223874
Publikováno v:
ICCE
In recent years, machine learning based on deep neural networks (DNN) is playing an increasingly important role. Artificial intelligence applications using DNN are achieving higher and higher accuracy levels. However, the multi-layer characteristic o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::93a4df9cd601952009a950ba48fc9152
https://doi.org/10.1109/icce.2016.7430525
https://doi.org/10.1109/icce.2016.7430525
Publikováno v:
IEEE Transactions on Consumer Electronics. 57:915-922
In this paper, we demonstrate a 2D-to-3D video conversion system capable of real-time 1920×1080p conversion. The proposed system generates 3D depth information by fusing cues from edge feature-based global scene depth gradient and texture-based loca
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9cc6c6dee0cc5e628cf2f7c534a6f51f
https://doi.org/10.1109/tce.2011.5955240
https://doi.org/10.1109/tce.2011.5955240
Publikováno v:
IEEE Transactions on Circuits and Systems for Video Technology. 19:1118-1128
Because video services are becoming popular on portable devices, power becomes the primary design issue for video coders nowadays. H.264/AVC is an emerging video coding standard which can provide outstanding coding performance and thus is suitable fo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::28f2b142789502b12da4db1ced09e4f5
https://doi.org/10.1109/tcsvt.2009.2020323
https://doi.org/10.1109/tcsvt.2009.2020323
Publikováno v:
Journal of Signal Processing Systems. 50:1-17
Data access usually leads to more than 50% of the power cost in a modern signal processing system. To realize a low-power design, how to reduce the memory access power is a critical issue. Data reuse (DR) is a technique that recycles the data read fr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b0538da068a19331a7098c4d3c0c0eee
https://doi.org/10.1007/s11265-007-0112-3
https://doi.org/10.1007/s11265-007-0112-3