Zobrazeno 1 - 10
of 313
pro vyhledávání: '"WU Zhennan"'
Autor:
Cui, Ruikai, Liu, Weizhe, Sun, Weixuan, Wang, Senbo, Shang, Taizhang, Li, Yang, Song, Xibin, Yan, Han, Wu, Zhennan, Chen, Shenzhou, Li, Hongdong, Ji, Pan
3D shape generation aims to produce innovative 3D content adhering to specific conditions and constraints. Existing methods often decompose 3D shapes into a sequence of localized components, treating each element in isolation without considering spat
Externí odkaz:
http://arxiv.org/abs/2403.18241
Autor:
Yan, Han, Li, Yang, Wu, Zhennan, Chen, Shenzhou, Sun, Weixuan, Shang, Taizhang, Liu, Weizhe, Chen, Tian, Dai, Xiaqiang, Ma, Chao, Li, Hongdong, Ji, Pan
We present Frankenstein, a diffusion-based framework that can generate semantic-compositional 3D scenes in a single pass. Unlike existing methods that output a single, unified 3D shape, Frankenstein simultaneously generates multiple separated shapes,
Externí odkaz:
http://arxiv.org/abs/2403.16210
Autor:
Wu, Zhennan, Li, Yang, Yan, Han, Shang, Taizhang, Sun, Weixuan, Wang, Senbo, Cui, Ruikai, Liu, Weizhe, Sato, Hiroyuki, Li, Hongdong, Ji, Pan
We present BlockFusion, a diffusion-based model that generates 3D scenes as unit blocks and seamlessly incorporates new blocks to extend the scene. BlockFusion is trained using datasets of 3D blocks that are randomly cropped from complete 3D scene me
Externí odkaz:
http://arxiv.org/abs/2401.17053
Publikováno v:
In Chemical Engineering Journal 15 November 2024 500
Autor:
Guo, Zining, Wang, Yuting, Liu, Wenhao, Huang, Haifu, Tang, Xiaorong, Wu, Zhennan, Lu, Liming, Fan, Baochao, Cui, Shaoyang, Xu, Nenggui
Publikováno v:
In Complementary Therapies in Medicine October 2024 85
Autor:
Lin, Yanling, Wu, Zhennan, Mei, Enrou, Yang, Jiapeng, He, Ye, Xu, Zhenbo, Liang, Xiaojuan, Hu, Xingen, Liu, Ruowang, Xiang, Weidong
Publikováno v:
In Applied Surface Science 1 March 2025 684
Autor:
Wu, Zhennan, Khardon, Roni
Stochastic planning can be reduced to probabilistic inference in large discrete graphical models, but hardness of inference requires approximation schemes to be used. In this paper we argue that such applications can be disentangled along two dimensi
Externí odkaz:
http://arxiv.org/abs/2203.12139
Autor:
Dong, Yinpeng, Fu, Qi-An, Yang, Xiao, Xiang, Wenzhao, Pang, Tianyu, Su, Hang, Zhu, Jun, Tang, Jiayu, Chen, Yuefeng, Mao, XiaoFeng, He, Yuan, Xue, Hui, Li, Chao, Liu, Ye, Zhang, Qilong, Gao, Lianli, Yu, Yunrui, Gao, Xitong, Zhao, Zhe, Lin, Daquan, Lin, Jiadong, Song, Chuanbiao, Wang, Zihao, Wu, Zhennan, Guo, Yang, Cui, Jiequan, Xu, Xiaogang, Chen, Pengguang
Due to the vulnerability of deep neural networks (DNNs) to adversarial examples, a large number of defense techniques have been proposed to alleviate this problem in recent years. However, the progress of building more robust models is usually hamper
Externí odkaz:
http://arxiv.org/abs/2110.08042
Publikováno v:
In Materials Today July 2024 76:72-93