Zobrazeno 1 - 10
of 1 099
pro vyhledávání: '"Zhu Xiangyang"'
Autor:
Zhu Xiangyang, Qiu Song, Liu Tong, Ding You, Tang Ruoyu, Liu Zhengliang, Chen Xiaocen, Ren Yuan
Publikováno v:
Nanophotonics, Vol 12, Iss 12, Pp 2157-2169 (2023)
In most rotational Doppler effect (RDE) measurements, the optical axis and the rotating axis of the object are required to be aligned. However, the condition is very difficult to achieve in practical applications of rotation detection, which seriousl
Externí odkaz:
https://doaj.org/article/f532b626be1c462bbc7b85c4d736d4d3
Autor:
Guo, Ziyu, Zhang, Renrui, Zhu, Xiangyang, Tong, Chengzhuo, Gao, Peng, Li, Chunyuan, Heng, Pheng-Ann
We introduce SAM2Point, a preliminary exploration adapting Segment Anything Model 2 (SAM 2) for zero-shot and promptable 3D segmentation. SAM2Point interprets any 3D data as a series of multi-directional videos, and leverages SAM 2 for 3D-space segme
Externí odkaz:
http://arxiv.org/abs/2408.16768
Autor:
Zhuo, Le, Du, Ruoyi, Xiao, Han, Li, Yangguang, Liu, Dongyang, Huang, Rongjie, Liu, Wenze, Zhao, Lirui, Wang, Fu-Yun, Ma, Zhanyu, Luo, Xu, Wang, Zehan, Zhang, Kaipeng, Zhu, Xiangyang, Liu, Si, Yue, Xiangyu, Liu, Dingning, Ouyang, Wanli, Liu, Ziwei, Qiao, Yu, Li, Hongsheng, Gao, Peng
Lumina-T2X is a nascent family of Flow-based Large Diffusion Transformers that establishes a unified framework for transforming noise into various modalities, such as images and videos, conditioned on text instructions. Despite its promising capabili
Externí odkaz:
http://arxiv.org/abs/2406.18583
Autor:
Zhu, Xiangyang, Zhang, Renrui, He, Bowei, Guo, Ziyu, Liu, Jiaming, Xiao, Han, Fu, Chaoyou, Dong, Hao, Gao, Peng
To reduce the reliance on large-scale datasets, recent works in 3D segmentation resort to few-shot learning. Current 3D few-shot segmentation methods first pre-train models on 'seen' classes, and then evaluate their generalization performance on 'uns
Externí odkaz:
http://arxiv.org/abs/2404.04050
Autor:
Guo, Ziyu, Zhang, Renrui, Zhu, Xiangyang, Tang, Yiwen, Ma, Xianzheng, Han, Jiaming, Chen, Kexin, Gao, Peng, Li, Xianzhi, Li, Hongsheng, Heng, Pheng-Ann
We introduce Point-Bind, a 3D multi-modality model aligning point clouds with 2D image, language, audio, and video. Guided by ImageBind, we construct a joint embedding space between 3D and multi-modalities, enabling many promising applications, e.g.,
Externí odkaz:
http://arxiv.org/abs/2309.00615
To reduce the reliance on large-scale datasets, recent works in 3D segmentation resort to few-shot learning. Current 3D few-shot semantic segmentation methods first pre-train the models on `seen' classes, and then evaluate their generalization perfor
Externí odkaz:
http://arxiv.org/abs/2308.12961
Recovering the shape and appearance of real-world objects from natural 2D images is a long-standing and challenging inverse rendering problem. In this paper, we introduce a novel hybrid differentiable rendering method to efficiently reconstruct the 3
Externí odkaz:
http://arxiv.org/abs/2308.10003
The popularity of Contrastive Language-Image Pre-training (CLIP) has propelled its application to diverse downstream vision tasks. To improve its capacity on downstream tasks, few-shot learning has become a widely-adopted technique. However, existing
Externí odkaz:
http://arxiv.org/abs/2304.01195
Autor:
Zhu, Xiangyang, Zhang, Renrui, He, Bowei, Guo, Ziyu, Zeng, Ziyao, Qin, Zipeng, Zhang, Shanghang, Gao, Peng
Large-scale pre-trained models have shown promising open-world performance for both vision and language tasks. However, their transferred capacity on 3D point clouds is still limited and only constrained to the classification task. In this paper, we
Externí odkaz:
http://arxiv.org/abs/2211.11682
Positioning with one inertial measurement unit and one ranging sensor is commonly thought to be feasible only when trajectories are in certain patterns ensuring observability. For this reason, to pursue observable patterns, it is required either exci
Externí odkaz:
http://arxiv.org/abs/2211.03093