Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Fu, Jianglin"'
We present CosmicMan, a text-to-image foundation model specialized for generating high-fidelity human images. Unlike current general-purpose foundation models that are stuck in the dilemma of inferior quality and text-image misalignment for humans, C
Externí odkaz:
http://arxiv.org/abs/2404.01294
Human generation has achieved significant progress. Nonetheless, existing methods still struggle to synthesize specific regions such as faces and hands. We argue that the main reason is rooted in the training data. A holistic human dataset inevitably
Externí odkaz:
http://arxiv.org/abs/2309.14335
Autor:
Fu, Jianglin, Li, Shikai, Jiang, Yuming, Lin, Kwan-Yee, Qian, Chen, Loy, Chen Change, Wu, Wayne, Liu, Ziwei
Unconditional human image generation is an important task in vision and graphics, which enables various applications in the creative industry. Existing studies in this field mainly focus on "network engineering" such as designing new components and o
Externí odkaz:
http://arxiv.org/abs/2204.11823
Autor:
Luo, Chunyi, Luo, Xin, Liu, Danyang, Ma, Guangmeng, Zhang, Longfei, Fu, Jianglin, Li, Yu, Guo, Fawei, Zhang, Mingtao, Long, Yu
Publikováno v:
In Chemical Engineering Journal 1 December 2024 501
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
We present two new fisheye image datasets for training face and object detection models: VOC-360 and Wider-360. The fisheye images are created by post-processing regular images collected from two well-known datasets, VOC2012 and Wider Face, using a m
Externí odkaz:
http://arxiv.org/abs/1906.11942
360-degree cameras offer the possibility to cover a large area, for example an entire room, without using multiple distributed vision sensors. However, geometric distortions introduced by their lenses make computer vision problems more challenging. I
Externí odkaz:
http://arxiv.org/abs/1902.02777
Autor:
Fu, Jianglin
Beamforming is a technique which can adaptively steer the pattern of a microphone array towards or away from a target direction. Three conventional beamforming techniques are reviewed and compared with a beamformer proposed here, called MVDR-2C. Most
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od_______497::8e8fed074891135bdeb6694eb848ebad
http://summit.sfu.ca/item/19952
http://summit.sfu.ca/item/19952
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Fu J; School of Engineering Science, Simon Fraser University, Burnaby, BC, V5A 1S6, Canada., Bajić IV; School of Engineering Science, Simon Fraser University, Burnaby, BC, V5A 1S6, Canada., Vaughan RG; School of Engineering Science, Simon Fraser University, Burnaby, BC, V5A 1S6, Canada.
Publikováno v:
Data in brief [Data Brief] 2019 Nov 02; Vol. 27, pp. 104752. Date of Electronic Publication: 2019 Nov 02 (Print Publication: 2019).