In this webinar hosted by the Color Technical Group, Vahid Babaei argues that data-driven approaches have an immense capacity for accurate and efficient appearance prediction. Unlike physical models that rely on the sophisticated relationship of highly specialized measurements, data-driven models count on the power of big but simple data to acquire. Babaei proposes a measurement-based data-driven performance space exploration of the color laser marking process. Babaei formulates this exploration as a search for the Pareto optimal solutions to multi-objective optimization and solves it using an evolutionary algorithm. The explored set of diverse colors is then utilized to mark high-quality, full-color images.

Subject Matter Level:

• Intermediate - Assumes basic knowledge of the topic

What You Will Learn:

• The novel trend of data-driven approaches for appearance reproduction
• The state of the novel hardware suitable for appearance reproduction

Who Should Attend:

• Scientists and engineers working in 3D printing at all career levels
• Professionals and practitioners in other fields interested in 3D printing

About the Presenter: Vahid Babaei, Max Planck Institute for Informatics

Vahid Babaei leads the AI-aided Design and Fabrication Group at the Computer Graphics Department of the Max Planck Institute for Informatics. He spent two years as a postdoctoral researcher at the Computer Science and Artificial Intelligence Laboratory (CSAIL) of the Massachusetts Institute of Technology (MIT). He obtained his Ph.D. in Computer Science from Ecole Polytechnique Fédérale de Lausanne (EPFL). His research interest lies at the intersection of manufacturing and computer science. His research aims to develop computational algorithms necessary for advanced manufacturing tools, such as multi-material 3D printers, to create products with novel, interesting and useful appearance specifications.