State of the Art B-Rep Generation using Machine Learning

Recorded at CDFAM Computational Design Symposium, NYC 2024Presentation AbstractBoundary representation (B-rep) 3D models are the standard 3D representation used in the manufacturing industry. However, only recently has machine learning research begun to make progress on generative models capable of producing B-rep models. This talk will give a summary of the current state of the art for generating B-rep models. In particular it will cover, BrepGen, our recent work using diffusion models, that have proved extremely successful in the image domain, to the problem of B-rep generation.Speaker BioKarl is a Senior Research Manager at Autodesk Research focused on data-driven design software for manufacturing. He holds a Ph.D. in Computational Design from Carnegie Mellon University and has presented his research internationally at conferences such as ICML, CVPR, ACM SIGGRAPH, ACM UIST, and ACM CHI. His work at Autodesk has won numerous awards including Fast Company Innovation By Design Honoree and Core77 Design Awards Research and Strategy Honoree.CDFAM Computational Design Symposium series brings together leading experts in computational design from industry, academia and software development for two days of knowledge sharing and networking. Visit CDFAM.COM to learn about upcoming events around the world. This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.designforam.com