Prosformer: Accurate Surface Reconstruction for Sparse Profilometer Measurement with Transformer
ID:68 View Protection:PUBLIC Updated Time:2022-12-22 10:02:51 Hits:152 Poster Presentation

Start Time:Pending(Asia/Shanghai)


Session:No Session »

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.
surface measurement;profilometer;neural networks
Jieji Ren
PhD Candidate Shanghai JiaoTong University

Submit Comment
Verify Code Change Another
All Comments
Important Date
  • Conference Date

    Nov 30



    Dec 02


  • Nov 30 2022

    Draft paper submission deadline

  • Dec 24 2022

    Contribution Submission Deadline

Sponsored By
Harbin Insititute of Technology
China Instrument and Control Society
Heilongjiang Instrument and Control Society
Chinese Institute of Electronics
IEEE I&M Society Harbin Chapter
Contact Information