Fast and accurate pose estimation of additive manufactured objects from few X-ray projections

作者：

Highlights：

• Our framework allows projection-based 3D inspection from very few images.

• CNN-based 3D pose estimation from one or multiple radiographs.

• High accuracy and precision demonstrated on simulated and measured data.

• Comparable to CT-based registration.

• Outperforms state-of-the-art DL-based 3D pose estimation from radiographs.

摘要

•Our framework allows projection-based 3D inspection from very few images.•CNN-based 3D pose estimation from one or multiple radiographs.•High accuracy and precision demonstrated on simulated and measured data.•Comparable to CT-based registration.•Outperforms state-of-the-art DL-based 3D pose estimation from radiographs.

论文关键词：Pose estimation,X-ray CT,Inspection,CNN,Radiography

论文评审过程：Received 11 April 2022, Revised 6 September 2022, Accepted 16 September 2022, Available online 22 September 2022, Version of Record 28 September 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.118866