机构

• 计算技术研究所 [1]
• 长春光学精密机械与物... [1]

采集方式

• OAI收割 [2]

内容类型

• 会议论文 [1]
• 期刊论文 [1]

发表日期

• 2023 [1]
• 2010 [1]

学科主题

筛选

浏览/检索结果: 共2条，第1-2条 帮助 条数/页： 5101520253035404550556065707580859095100 排序方式： 请选择题名升序题名降序提交时间升序提交时间降序作者升序作者降序发表日期升序发表日期降序 CoAxNN: Optimizing on-device deep learning with conditional approximate neural networks 期刊论文  OAI收割 JOURNAL OF SYSTEMS ARCHITECTURE, 2023, 卷号: 143, 页码: 14 作者:  Li, Guangli;  Ma, Xiu;  Yu, Qiuchu;  Liu, Lei;  Liu, Huaxiao   |  收藏  |  浏览/下载：18/0  |  提交时间：2023/12/04 On-device deep learning  Efficient neural networks  Model approximation and optimization   Animated models coarsening with local area distortion and deformation degree control (EI CONFERENCE) 会议论文  OAI收割 International Conference on Image Processing and Pattern Recognition in Industrial Engineering, August 7, 2010 - August 8, 2010, Xi'an, China 作者:  Zhang S.;  Zhao J. 收藏  |  浏览/下载：21/0  |  提交时间：2013/03/25 In computer graphics applications  mesh coarsening is an important technique to alleviate the workload of visualization processing. Compared to the extensive works on static model approximation  very little attentions have been paid to animated models. In this paper  we propose a new method to approximate animated models with local area distortion and deformation degree control. Our method uses an improved quadric error metric guided by a local area distortion measurement as a basic hierarchy. Also  we define a deformation degree parameter to be embedded into the aggregated quadric errors  so areas with large deformation during the animation can be successfully preserved. Finally  a mesh optimization process is proposed to further reduce the geometric distortion for each frame. Our approach is fast  easy to implement  and as a result good quality dynamic approximations with well-preserved sharp features can be generated at any given frame. 2010 SPIE.