Zobrazeno 1 - 10
of 489
pro vyhledávání: '"HU, Mu"'
Autor:
Hu, Mu, Yin, Wei, Zhang, Chi, Cai, Zhipeng, Long, Xiaoxiao, Wang, Kaixuan, Chen, Hao, Yu, Gang, Shen, Chunhua, Shen, Shaojie
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 46, no. 12, pp. 10579-10596, 2024
We introduce Metric3D v2, a geometric foundation model for zero-shot metric depth and surface normal estimation from a single image, which is crucial for metric 3D recovery. While depth and normal are geometrically related and highly complimentary, t
Externí odkaz:
http://arxiv.org/abs/2404.15506
Autor:
Fu, Xiao, Yin, Wei, Hu, Mu, Wang, Kaixuan, Ma, Yuexin, Tan, Ping, Shen, Shaojie, Lin, Dahua, Long, Xiaoxiao
We introduce GeoWizard, a new generative foundation model designed for estimating geometric attributes, e.g., depth and normals, from single images. While significant research has already been conducted in this area, the progress has been substantial
Externí odkaz:
http://arxiv.org/abs/2403.12013
Publikováno v:
Xiehe Yixue Zazhi, Vol 15, Iss 5, Pp 987-992 (2024)
During the 14th Five-Year Plan period, public hospitals in China have entered a phase of high-quality development, with health insurance payment system reforms becoming a crucial means to promote this advancement. However, from the current situation,
Externí odkaz:
https://doaj.org/article/228ecdc48c2f4ffc815f33736a72b74a
Autor:
Hu, Mu, Feng, Junyi, Hua, Jiashen, Lai, Baisheng, Huang, Jianqiang, Gong, Xiaojin, Hua, Xiansheng
Structural re-parameterization has drawn increasing attention in various computer vision tasks. It aims at improving the performance of deep models without introducing any inference-time cost. Though efficient during inference, such models rely heavi
Externí odkaz:
http://arxiv.org/abs/2204.00826
Publikováno v:
In Materials Today Bio August 2024 27
Channel estimation is one of the key issues in practical massive multiple-input multiple-output (MIMO) systems. Compared with conventional estimation algorithms, deep learning (DL) based ones have exhibited great potential in terms of performance and
Externí odkaz:
http://arxiv.org/abs/2108.09430
Image guided depth completion is the task of generating a dense depth map from a sparse depth map and a high quality image. In this task, how to fuse the color and depth modalities plays an important role in achieving good performance. This paper pro
Externí odkaz:
http://arxiv.org/abs/2103.00783
Autor:
Chen, Xing-Juan, Liu, Si-Yuan, Li, Si-Ming, Feng, Ji-Kang, Hu, Ying, Cheng, Xiao-Zhen, Hou, Cheng-Zhi, Xu, Yun, Hu, Mu, Feng, Ling, Xiao, Lu
Publikováno v:
In Heliyon 15 March 2024 10(5)
Publikováno v:
In Journal of the Taiwan Institute of Chemical Engineers February 2024 155