Zobrazeno 1 - 10
of 151
pro vyhledávání: '"Thrasyvoulos N. Pappas"'
Publikováno v:
e-Prime: Advances in Electrical Engineering, Electronics and Energy, Vol 6, Iss , Pp 100286- (2023)
We investigate data-driven texture modeling via analysis and synthesis with generative adversarial networks. For network training and testing, we have compiled a diverse set of spatially homogeneous textures, ranging from stochastic to regular. We ad
Externí odkaz:
https://doaj.org/article/0abff73be0474fddac1f59b2e94d729c
Publikováno v:
e-Prime: Advances in Electrical Engineering, Electronics and Energy, Vol 3, Iss , Pp 100092- (2023)
We present a universal texture synthesis approach that incorporates a novel multiscale texton broadcasting module in the StyleGAN-2 framework. The texton broadcasting module introduces an inductive bias, enabling generation of a broader range of text
Externí odkaz:
https://doaj.org/article/2c1b3f41dc874d4fade77eca876d59cd
Publikováno v:
IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 31
We present a pattern-based approach for reconstructing a K-level image from cutsets, dense samples taken along a family of lines or curves in two- or three-dimensional space, which break the image into blocks, each of which is typically reconstructed
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0ff5310bd442c9b43b964771d1212295
https://pubmed.ncbi.nlm.nih.gov/35951565
https://pubmed.ncbi.nlm.nih.gov/35951565
Publikováno v:
IEEE Transactions on Image Processing. 30:3610-3622
We propose objective, image-based techniques for quantitative evaluation of facial skin gloss that is consistent with human judgments. We use polarization photography to obtain separate images of surface and subsurface reflections, and rely on psycho
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::82f2014ef7212689e3d956a13d429cb3
https://doi.org/10.1109/tip.2021.3061276
https://doi.org/10.1109/tip.2021.3061276
We present a new approach for universal texture synthesis by incorporating a multi-scale texton broadcasting module in the StyleGAN-2 framework. The texton broadcasting module introduces an inductive bias, enabling generation of broader range of text
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b59036d7193476865a3137968f3c9a9e
Publikováno v:
IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 30
We consider lossy compression of a broad class of bilevel images that satisfy the smoothness criterion, namely, images in which the black and white regions are separated by smooth or piecewise smooth boundaries, and especially lossy compression of co
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c84af191569262b0c69bfbaf408372a8
https://pubmed.ncbi.nlm.nih.gov/33360989
https://pubmed.ncbi.nlm.nih.gov/33360989
Autor:
Sterling S. Rooke, Yatish Kumar, Stijn Wielandt, Pete Beckman, Kevin J. Barker, Trever Pfeffer, Klaehn Burkes, Lena Mashayekhy, Veroica Tribaldos, Randall Berry, Praveen Kumar, Johnathan Vee Cree, A. Evdokimov, Yuxin Wu, Robert Kozma, Suhas Somnath, Moinuddin Ahmed, Franck Cappello, Bin Wang, Rose Yu, Andrew Wiedlea, Marius Stan, Linquan Bai, Angela Wang, Dipankar Dasgupta, Cory Stuart, Colby Harper, Thrasyvoulos N. Pappas, Alec Sandy, Nicholas Schwarz, Peter L. Fuhr, Prasanna Balaprakash, Jason Fields, Shaloo Rakheja, Bill Nickless, Ryan C. Sullivan, Greg Tchilinguirian, Yier Jin, Zhi Yao, Mohammed Alawad, Arun Veeramany, Gordon J. Brebner, Anastasiia Butko, Inder Monga, Yuping Zeng, Rajesh Sankaran, Tarek Saadawi, Charlie Catlett, Xi Yang, Linqing Luo, Arup Bhuyan, Theresa L. Windus, Nhan Tran, Rajkumar Kettimuthu, Scott Collis, Sumit Roy, Anirudha V. Sumant, Yuepeng Zhang, Mariam Kiran, Ryan Chard, Elena S. Peterson
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e8295cddf24cc1b8e0239b85c2f13919
https://doi.org/10.2172/1606538
https://doi.org/10.2172/1606538
Autor:
Jue Lin, Thrasyvoulos N. Pappas
Publikováno v:
ICIP
We propose a new direct approach for material recognition under diverse illumination and viewing conditions based on visual texture. We apply K-means clustering to feature vectors that consist of steerable filter subband statistics and dominant color
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b5456beda34867860684cc67f11bda90
https://doi.org/10.1109/icip.2019.8803648
https://doi.org/10.1109/icip.2019.8803648