Researchers propose CAD-based method to identify new 3D printed parts without retraining

• Researchers from KU Leuven, Materialise, a 3D printing software and services company, and Iristick, which develops industrial smart glasses, have proposed a method for classifying new 3D printed objects without retraining a vision model each time a new part enters production. Described in a paper published on arXiv, the system uses CAD models to identify […]

Researchers from KU Leuven, Materialise, a 3D printing software and services company, and Iristick, which develops industrial smart glasses, have proposed a method for classifying new 3D printed objects without retraining a vision model each time a new part enters production. Described in a paper published on arXiv, the system uses CAD models to identify printed parts after fabrication, addressing a step that remains largely manual in additive manufacturing workflows. Alongside the method, the researchers introduced ThingiPrint, a public dataset pairing CAD models with photographs of their 3D printed counterparts. Post-production identification remains a practical problem in additive manufacturing because multiple parts are often produced in a single build and later collected together for