Zobrazeno 1 - 10
of 1 405
pro vyhledávání: '"CAO Zhiguo"'
Autor:
ZHANG Haiqin, BAO Yixiang, TANG Jiawei, CAO Zhiguo, JIANG Binbin, LI Jie, LI Jingfeng, LIU Zhaofeng
Publikováno v:
Meitan kexue jishu, Vol 51, Iss 2, Pp 436-448 (2023)
As coal mining is shifted to the deep in Shendong mining area and fluorine concentration in mine water is increasing, it is of great significance to study the main sources of fluoride for the control of fluoride pollution in mine water. In order to f
Externí odkaz:
https://doaj.org/article/acebd13e4230441a842edc440b12531e
Publikováno v:
Meikuang Anquan, Vol 53, Iss 2, Pp 93-98 (2022)
In order to protect and utilize water resources in coal mining, academician GU Dazhao has put forward the theoretical framework and technical system of coal mine underground reservoir with “guiding storage and use” as the core after 20 years of t
Externí odkaz:
https://doaj.org/article/93d843563cdc4606bc3aae0002e5e45c
Autor:
Li, Jiaqi, Wang, Yiran, Zheng, Jinghong, Huang, Zihao, Xian, Ke, Cao, Zhiguo, Zhang, Jianming
Depth refinement aims to infer high-resolution depth with fine-grained edges and details, refining low-resolution results of depth estimation models. The prevailing methods adopt tile-based manners by merging numerous patches, which lacks efficiency
Externí odkaz:
http://arxiv.org/abs/2409.17880
We study the problem of generating intermediate images from image pairs with large motion while maintaining semantic consistency. Due to the large motion, the intermediate semantic information may be absent in input images. Existing methods either li
Externí odkaz:
http://arxiv.org/abs/2409.09605
Publikováno v:
矿业科学学报, Vol 6, Iss 2, Pp 244-254 (2021)
The acquisition and communication of ecological and environmental risk information can effectively mitigate the social risks caused by ecological and environmental damage in coal power base.According to the risk information seeking and processing mod
Externí odkaz:
https://doaj.org/article/6136a19d0ccd4ae6b8225bc0f16bf5bf
The labelling difficulty has been a longstanding problem in deep image matting. To escape from fine labels, this work explores using rough annotations such as trimaps coarsely indicating the foreground/background as supervision. We present that the c
Externí odkaz:
http://arxiv.org/abs/2408.10539
Autor:
Zhang, Junrui, Li, Jiaqi, Huang, Yachuan, Wang, Yiran, Zheng, Jinghong, Shen, Liao, Cao, Zhiguo
In the field of monocular depth estimation (MDE), many models with excellent zero-shot performance in general scenes emerge recently. However, these methods often fail in predicting non-Lambertian surfaces, such as transparent or mirror (ToM) surface
Externí odkaz:
http://arxiv.org/abs/2408.06083
Autor:
Li, Xingyi, Wu, Yizheng, Cen, Jun, Peng, Juewen, Wang, Kewei, Xian, Ke, Wang, Zhe, Cao, Zhiguo, Lin, Guosheng
3D content creation has long been a complex and time-consuming process, often requiring specialized skills and resources. While recent advancements have allowed for text-guided 3D object and scene generation, they still fall short of providing suffic
Externí odkaz:
http://arxiv.org/abs/2408.01678
The goal of this work is to develop a task-agnostic feature upsampling operator for dense prediction where the operator is required to facilitate not only region-sensitive tasks like semantic segmentation but also detail-sensitive tasks such as image
Externí odkaz:
http://arxiv.org/abs/2407.13500
High dynamic range (HDR) video rendering from low dynamic range (LDR) videos where frames are of alternate exposure encounters significant challenges, due to the exposure change and absence at each time stamp. The exposure change and absence make exi
Externí odkaz:
http://arxiv.org/abs/2407.13309