Prosformer: Accurate Surface Reconstruction for Sparse Profilometer Measurement with Transformer
编号:68 访问权限:公开 更新:2022-12-22 10:02:51 浏览:350次 张贴报告

报告开始:暂无开始时间(Asia/Shanghai)

报告时间:暂无持续时间

所在会场:[暂无会议] [暂无会议段]

摘要
Surface micro-structure measurement is significant for precision manufacturing. However, existing stylus profilometer is inefficient, and sparse line-scan measurement can’t support accurate surface description. To improve the reconstruction performance, we propose a high-accurate reconstruction method  with sparse line-scan measurement based on attention mechanism. We first arrange the sparse-line measurement in the 2D matrix and crop as patch region. Then we utilize transformer to construct semantic relationships between patches and assign  new weights to each patch to accurately model the structural relationships of target region and perform feature extraction, where the self-attention can enhance the description of local details while cross-attention will interact with global information. Finally, a fully connected network as a decoder is adopted to  reconstruct accurate surface details with complete geometric representation. We refer to this model as Prosformer. Furthermore, we simulate a larger-scale surface micro-structure dataset to drive the training process and measure micro-structures to valid Prosformer. Experiments show proposed method can effectively restore complex surface details.
关键词
surface measurement;profilometer;neural networks
报告人
Jieji Ren
PhD Candidate Shanghai JiaoTong University

发表评论
验证码 看不清楚,更换一张
全部评论
重要日期
  • 会议日期

    11月30日

    2022

    12月02日

    2022

  • 11月30日 2022

    初稿截稿日期

  • 12月24日 2022

    报告提交截止日期

  • 04月13日 2023

    注册截止日期

主办单位
Harbin Insititute of Technology
China Instrument and Control Society
Heilongjiang Instrument and Control Society
Chinese Institute of Electronics
IEEE I&M Society Harbin Chapter
联系方式
移动端
在手机上打开
小程序
打开微信小程序
客服
扫码或点此咨询