Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Zhou, Zanwei"'
Autor:
Yi, Taoran, Fang, Jiemin, Zhou, Zanwei, Wang, Junjie, Wu, Guanjun, Xie, Lingxi, Zhang, Xiaopeng, Liu, Wenyu, Wang, Xinggang, Tian, Qi
Recently, 3D Gaussian splatting (3D-GS) has achieved great success in reconstructing and rendering real-world scenes. To transfer the high rendering quality to generation tasks, a series of research works attempt to generate 3D-Gaussian assets from t
Externí odkaz:
http://arxiv.org/abs/2406.18462
Autor:
Cen, Jiazhong, Fang, Jiemin, Zhou, Zanwei, Yang, Chen, Xie, Lingxi, Zhang, Xiaopeng, Shen, Wei, Tian, Qi
The Segment Anything Model (SAM) emerges as a powerful vision foundation model to generate high-quality 2D segmentation results. This paper aims to generalize SAM to segment 3D objects. Rather than replicating the data acquisition and annotation proc
Externí odkaz:
http://arxiv.org/abs/2304.12308
Autor:
Yang, Chen, Li, Peihao, Zhou, Zanwei, Yuan, Shanxin, Liu, Bingbing, Yang, Xiaokang, Qiu, Weichao, Shen, Wei
We present NeRFVS, a novel neural radiance fields (NeRF) based method to enable free navigation in a room. NeRF achieves impressive performance in rendering images for novel views similar to the input views while suffering for novel views that are si
Externí odkaz:
http://arxiv.org/abs/2304.06287
Multivariate time series forecasting (MTSF) is a fundamental problem in numerous real-world applications. Recently, Transformer has become the de facto solution for MTSF, especially for the long-term cases. However, except for the one forward operati
Externí odkaz:
http://arxiv.org/abs/2212.02789
Conversation is an essential component of virtual avatar activities in the metaverse. With the development of natural language processing, textual and vocal conversation generation has achieved a significant breakthrough. However, face-to-face conver
Externí odkaz:
http://arxiv.org/abs/2203.07931
Autor:
Cen, Jiazhong, Zhou, Zanwei, Fang, Jiemin, Yang, Chen, Shen, Wei, Xie, Lingxi, Jiang, Dongsheng, Zhang, Xiaopeng, Tian, Qi
Recently, the Segment Anything Model (SAM) emerged as a powerful vision foundation model which is capable to segment anything in 2D images. This paper aims to generalize SAM to segment 3D objects. Rather than replicating the data acquisition and anno
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6c1e74dd94eb751827705ae776cde99d
Autor:
Zhou, Zanwei, Wang, Zi, Yao, Shunyu, Yan, Yichao, Yang, Chen, Zhai, Guangtao, Yan, Junchi, Yang, Xiaokang
Conversation is an essential component of virtual avatar activities in the metaverse. With the development of natural language processing, textual and vocal conversation generation has achieved a significant breakthrough. Face-to-face conversations a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9561855739c4ff51cd4f59fa8855a4d4
http://arxiv.org/abs/2203.07931
http://arxiv.org/abs/2203.07931