期刊文献+
共找到2篇文章
< 1 >
每页显示 20 50 100
Methodology of High Accuracy and Resolution 3D Geological Model Generation and Application
1
作者 吴键 曹代勇 +3 位作者 邓爱居 李东津 蒋涛 翟光华 《Journal of China University of Mining and Technology》 2004年第1期47-50,共4页
By generating a high accuracy and high resolution geological model in Liuchu oil field, the technique of geological modeling is expanded and involved in primary geological study, making the sand bodies and reservoir b... By generating a high accuracy and high resolution geological model in Liuchu oil field, the technique of geological modeling is expanded and involved in primary geological study, making the sand bodies and reservoir be easily described in detail. The 3D visualization and 3D interactive editing of geological structure model are the key for modeling procedure. And a high accuracy and resolution geological model has been well applied in optimizing the production scheme. 展开更多
关键词 high accuracy and resolution 3D visualization interactive editing production scheme
在线阅读 下载PDF
DeepFaceReshaping:Interactive deep face reshaping via landmark manipulation
2
作者 Shu-Yu Chen Yue-Ren Jiang +4 位作者 Hongbo Fu Xinyang Han Zitao Liu Rong Li Lin Gao 《Computational Visual Media》 SCIE EI CSCD 2024年第5期949-963,共15页
Deep generative models allow the synthesis of realistic human faces from freehand sketches or semantic maps.However,although they are flexible,sketches and semantic maps provide too much freedom for manipulation,and t... Deep generative models allow the synthesis of realistic human faces from freehand sketches or semantic maps.However,although they are flexible,sketches and semantic maps provide too much freedom for manipulation,and thus,are not easy for novice users to control.In this study,we present DeepFaceReshaping,a novel landmarkbased deep generative framework for interactive face reshaping.To edit the shape of a face realistically by manipulating a small number of face landmarks,we employ neural shape deformation to reshape individual face components.Furthermore,we propose a novel Transformer-based partial refinement network to synthesize the reshaped face components conditioned on the edited landmarks,and fuse the components to generate the entire face using a local-to-global approach.In this manner,we limit possible reshaping effects within a feasible component-based face space.Thus,our interface is intuitive even for novice users,asconfirmed by auser study.Our experiments demonstrate that our method outperforms traditional warping-based approaches and recent deep generative techniques. 展开更多
关键词 face reshaping deep generative model interactive editing
原文传递
上一页 1 下一页 到第
使用帮助 返回顶部