Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Jiao, Nianhong"'
We propose an effective method for inserting adapters into text-to-image foundation models, which enables the execution of complex downstream tasks while preserving the generalization ability of the base model. The core idea of this method is to opti
Externí odkaz:
http://arxiv.org/abs/2410.22901
Autor:
Yan, Haonan, Chen, Jiaqi, Zhang, Xujie, Zhang, Shengkai, Jiao, Nianhong, Liang, Xiaodan, Zheng, Tianxiang
Publikováno v:
ICCV 2021
Recovering dense human poses from images plays a critical role in establishing an image-to-surface correspondence between RGB images and the 3D surface of the human body, serving the foundation of rich real-world applications, such as virtual humans,
Externí odkaz:
http://arxiv.org/abs/2110.15267
3D face reconstruction from a single image is a challenging problem, especially under partial occlusions and extreme poses. This is because the uncertainty of the estimated 2D landmarks will affect the quality of face reconstruction. In this paper, w
Externí odkaz:
http://arxiv.org/abs/2007.03979
Publikováno v:
Computer Graphics Forum. Oct2018, Vol. 37 Issue 7, p361-371. 11p. 11 Diagrams, 3 Charts.
Publikováno v:
Computer Graphics Forum. 37:361-371
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b2e087b58c18e0dbb299d94a98a93e25
https://doi.org/10.1111/cgf.13574
https://doi.org/10.1111/cgf.13574