Zobrazeno 1 - 10
of 51
pro vyhledávání: '"Yan, Zizheng"'
Autor:
Yan, Zizheng, Zhou, Jiapeng, Meng, Fanpeng, Wu, Yushuang, Qiu, Lingteng, Ye, Zisheng, Cui, Shuguang, Chen, Guanying, Han, Xiaoguang
Text-to-3D generation has recently seen significant progress. To enhance its practicality in real-world applications, it is crucial to generate multiple independent objects with interactions, similar to layer-compositing in 2D image editing. However,
Externí odkaz:
http://arxiv.org/abs/2407.16260
In this paper, we introduce a realistic and challenging domain adaptation problem called Universal Semi-supervised Model Adaptation (USMA), which i) requires only a pre-trained source model, ii) allows the source and target domain to have different l
Externí odkaz:
http://arxiv.org/abs/2307.03449
Autor:
Wu, Yushuang, Yan, Zizheng, Chen, Ce, Wei, Lai, Li, Xiao, Li, Guanbin, Li, Yihao, Cui, Shuguang, Han, Xiaoguang
Publikováno v:
CVPR 2023
3D shape completion from point clouds is a challenging task, especially from scans of real-world objects. Considering the paucity of 3D shape ground truths for real scans, existing works mainly focus on benchmarking this task on synthetic data, e.g.
Externí odkaz:
http://arxiv.org/abs/2304.10179
Autor:
Yu, Xianggang, Xu, Mutian, Zhang, Yidan, Liu, Haolin, Ye, Chongjie, Wu, Yushuang, Yan, Zizheng, Zhu, Chenming, Xiong, Zhangyang, Liang, Tianyou, Chen, Guanying, Cui, Shuguang, Han, Xiaoguang
Being data-driven is one of the most iconic properties of deep learning algorithms. The birth of ImageNet drives a remarkable trend of "learning from large-scale data" in computer vision. Pretraining on ImageNet to obtain rich universal representatio
Externí odkaz:
http://arxiv.org/abs/2303.06042
Semi-supervised domain adaptation (SSDA) aims to apply knowledge learned from a fully labeled source domain to a scarcely labeled target domain. In this paper, we propose a Multi-level Consistency Learning (MCL) framework for SSDA. Specifically, our
Externí odkaz:
http://arxiv.org/abs/2205.04066
Autor:
Wu, Yushuang, Yan, Zizheng, Cai, Shengcai, Li, Guanbin, Yu, Yizhou, Han, Xiaoguang, Cui, Shuguang
Semantic segmentation of point cloud usually relies on dense annotation that is exhausting and costly, so it attracts wide attention to investigate solutions for the weakly supervised scheme with only sparse points annotated. Existing works start fro
Externí odkaz:
http://arxiv.org/abs/2202.10705
Autor:
Lin, Yiqun, Yan, Zizheng, Huang, Haibin, Du, Dong, Liu, Ligang, Cui, Shuguang, Han, Xiaoguang
We introduce FPConv, a novel surface-style convolution operator designed for 3D point cloud analysis. Unlike previous methods, FPConv doesn't require transforming to intermediate representation like 3D grid or graph and directly works on surface geom
Externí odkaz:
http://arxiv.org/abs/2002.10701
Autor:
Zhu, Tianqi, Zhang, Liang, Yan, Zizheng, Liu, Bowen, Li, Youyue, You, Xiangkai, Chen, Mo-Xian, Liu, Tie-Yuan, Xu, Yuefei, Zhang, Jianhua
Publikováno v:
In Industrial Crops & Products 15 December 2023 206
Publikováno v:
In Computers & Graphics November 2023 116:427-436
Visual tracking is fragile in some difficult scenarios, for instance, appearance ambiguity and variation, occlusion can easily degrade most of visual trackers to some extent. In this paper, visual tracking is empowered with wireless positioning to ac
Externí odkaz:
http://arxiv.org/abs/1903.03736