论文部分内容阅读
[!--newstext--]
[!--title--]
【摘 要】
：
We present neural compositing,a deep-learning based method for augmented reality rendering,which uses convolutional neural networks to composite rendered layers
【机 构】
：
State Key Lab of CAD&CG,Zhejiang University,Hangzhou 310058,China;State Key Lab of CAD&CG,Zhejiang U
【出 处】
：
中国科学：信息科学（英文版）
【发表日期】
：
2021年2期
其他文献
Dear editor,rnDuring the past few decades,a significant amount of at-tention has been focused on deterministic time-delay sys-tems.These studies are based on al
期刊
Switched systems,i.e.,systems changing the parameter values(even structural forms)abruptly and randomly at arbitrary instants,have been extensively utilized in
Transition metal oxides have high specific capacity as anode materials for lithium-ion battery.But aggregation of particles and volume expansion during lithiati
Multiple instance learning (MIL) assigns a single class label to a bag of instances tailored for some real-world applications such as drug activity prediction.C
With the significant development of unmanned aerial vehicles (UAVs) technologies,a rapid increase on the use of UAV swarms in a wide range of civilian and emerg
To realize the high-efficiency acquisition of environmental mechanical energy,traditional triboelectric nanogenerators (TENGs) based on contact-separation consi
Dear editor,rnLow-rank tensor recovery(LRTR)[1]is a natural higher-order generalization of the compressed sensing(CS)[2]and the low-rank matrix recovery(LRMR)[3
期刊
Realization of robust quantum computing is a tremendous task.On one hand,one must reduce errors as many as pos-sible using various means[1-3];on the other hand,
期刊
近年来,北京汽车股份有限公司汽车研究院结合自主研发高端人才培养需求的实际,在研发人才培养工作方面不断创新,探索并形成了具有汽车研发特色的“匠研·隧穿”研发人才培养
期刊