Zobrazeno 1 - 10
of 17
pro vyhledávání: '"Stavros Tsogkas"'
Autor:
Sven Dickinson, Kaleem Siddiqi, Xiang Bai, Yongchao Xu, Jianqiang Wan, Yukang Wang, Stavros Tsogkas
Publikováno v:
International Journal of Computer Vision. 129:1323-1339
The medial axis, or skeleton, is a fundamental object representation that has been extensively used in shape recognition. Yet, its extension to natural images has been challenging due to the large appearance and scale variations of objects and comple
Autor:
Dylan Turpin, Liquan Wang, Eric Heiden, Yun-Chun Chen, Miles Macklin, Stavros Tsogkas, Sven Dickinson, Animesh Garg
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031200670
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::408c5767f6d6114ef3143b47949c4084
https://doi.org/10.1007/978-3-031-20068-7_12
https://doi.org/10.1007/978-3-031-20068-7_12
Publikováno v:
Robotics: Science and Systems
Tool use requires reasoning about the fit between an object's affordances and the demands of a task. Visual affordance learning can benefit from goal-directed interaction experience, but current techniques rely on human labels or expert demonstration
A complete representation of 3D objects requires characterizing the space of deformations in an interpretable manner, from articulations of a single instance to changes in shape across categories. In this work, we improve on a prior generative model
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e9eb8666797d032c0360a5983e21afe4
Publikováno v:
Computer Vision – ECCV 2020 Workshops ISBN: 9783030670696
ECCV Workshops (3)
ECCV Workshops (3)
Deep learning methods for super-resolution (SR) have been dominating in terms of performance in recent years. Such methods can potentially improve the digital zoom capabilities of most modern mobile phones, but are not directly applicable on device,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::787461b6bcec375fdbe753d29b5ab233
https://doi.org/10.1007/978-3-030-67070-2_5
https://doi.org/10.1007/978-3-030-67070-2_5
Autor:
Tristan Aumentado-Armstrong, Allan D. Jepson, Alex Levinshtein, Stavros Tsogkas, Konstantinos G. Derpanis
Publikováno v:
3DV
For humans, visual understanding is inherently generative: given a 3D shape, we can postulate how it would look in the world; given a 2D image, we can infer the 3D structure that likely gave rise to it. We can thus translate between the 2D visual and
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ebba8a0c7704c4c9f9f0e22ab310556b
Autor:
Nan Nan, Stavros Tsogkas, Geun-Woo Jeon, Jun-Hyuk Kim, Xiaochuan Li, Jiande Jiang, Xiaotong Luo, Lei Zhang, Jun-Ho Choi, Vineeth Bhaskara, Yuzhi Zhao, Jong-Seok Lee, Shuai Liu, Maitreya Suin, Jian Cheng, Xiaohong Liu, Xuehui Wang, Jiangtao Nie, Wenyi Wang, Siang Chen, Martin Danelljan, Jiangtao Zhang, Rushi Lan, Yawei Li, Long Chen, Yu Zhu, Allan D. Jepson, Cong Leng, Christian Micheloni, Jie Cai, Shanshan Zhao, Chenghua Li, Rao Muhammad Umer, Guangyang Wu, C. V. Jiji, Zhenbing Liu, Zibo Meng, Eric Marty, Xinbo Gao, Qiong Yan, Wenhao Wang, Wei Wei, Subin Yang, A. N. Rajagopalan, Wen Lu, Radu Timofte, Jie Liu, Long Sun, Yu Qiao, Haicheng Wang, Yanyun Qu, Yongwoo Kim, Tongtong Zhao, Alex Levinshtein, Steven Marty, Wenjie Xu, JungHeum Kang, Xiangtao Kong, Xiangyu He, Densen Puthussery, Jie Tang, Jingwen He, Kai Zhang, Lin Zha, P. S. Hrishikesh, Hengyuan Zhao, Chao Dong, Sung-Ho Bae, Zhiqiang Lang, Abdul Muqeet, Xiangzhen Kong, Jiaming Ding, Dongliang Xiong, Chiu Man Ho, Jiwon Hwang, Gangshan Wu, Liang Chen, Kuldeep Purohit
Publikováno v:
Computer Vision – ECCV 2020 Workshops ISBN: 9783030670696
ECCV Workshops (3)
ECCV Workshops (3)
This paper reviews the AIM 2020 challenge on efficient single image super-resolution with focus on the proposed solutions and results. The challenge task was to super-resolve an input image with a magnification factor \(\times \)4 based on a set of p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d21d570f8d10ec09dfbf7bc40c5c9c4a
https://doi.org/10.1007/978-3-030-67070-2_1
https://doi.org/10.1007/978-3-030-67070-2_1
Autor:
Anders Eriksson, Mateusz Michalkiewicz, Eugene Belilovsky, Stavros Tsogkas, Mahsa Baktashmotlagh, Sarah Parisot
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585945
ECCV (25)
ECCV (25)
The impressive performance of deep convolutional neural networks in single-view 3D reconstruction suggests that these models perform non-trivial reasoning about the 3D structure of the output space. Recent work has challenged this belief, showing tha
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c4311f9b5cdcc6484635f015447a6e0d
https://doi.org/10.1007/978-3-030-58595-2_37
https://doi.org/10.1007/978-3-030-58595-2_37
Publikováno v:
ICCV
Representing 3D shape is a fundamental problem in artificial intelligence, which has numerous applications within computer vision and graphics. One avenue that has recently begun to be explored is the use of latent representations of generative model
Publikováno v:
CVPR
Computing object skeletons in natural images is challenging, owing to large variations in object appearance and scale, and the complexity of handling background clutter. Many recent methods frame object skeleton detection as a binary pixel classifica
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6fc4588c7946d9807feebeabce3cb81f
http://arxiv.org/abs/1811.12608
http://arxiv.org/abs/1811.12608