Mohammad Sadil Khan
| E-Mail: | Mohammad.Khan@dfki.de |
|---|---|
| Position: | Researcher |
I am currently pursuing a PhD degree with the German Research Center for Artificial Intelligence (DFKI GmbH) and the University of Kaiserslautern-Landau (RPTU), under the supervision of Prof. Dr Didier Stricker. My research includes 3D Scene and Shape understanding with Vision-Language models and AI Assisted Computer-Aided Design (CAD) modeling.
Our NeurIPS Spotlight paper “Text2CAD: Generating Sequential CAD Designs from Beginner-To-Expert Level Text Prompts” proposes the first AI framework for generating parametric CAD models from text prompts of varying abstraction level.
You can check out my homepage and google scholar for more info.
Note: I am currently looking for HiWis who are interested in AI-Aided CAD Modeling, 3D Shape Reconstruction or Text to 3D/4D Content Creation. The ideal candidates should have experience in Pytorch. Please send me your resume if you want to work with us.
MARVEL-40M+: Multi-Level Visual Elaboration for High-Fidelity Text-to-3D Content Creation
In: In Proceedings of the Forty-Second Annual Conference on Computer Vision and Pattern Recognition (CVPR-25). International Conference on Computer Vision and Pattern Recognition (CVPR-2025), Nashville, Tennessee, USA, IEEE/CVF, 2025.
Details
| Link 1
Text2CAD: Generating Sequential CAD Models from Beginner-to-Expert Level Text Prompts
In: The Thirty-Eighth Annual Conference on Neural Information Processing Systems. Neural Information Processing Systems (NeurIPS-2024), December 10-15, Vancouver, British Columbia, Canada, Pages 7552-7579, Vol. 37, Neural Information Processing Systems, 1/2025.
Details
| Link 1
BRep Boundary and Junction Detection for CAD Reverse Engineering
In: Proceedings of the 3rd IEEE International Conference on Computing and Machine Intelligence. IEEE International Conference on Computing and Machine Intelligence (ICMI-2024), April 13-14, Michigan, MI, USA, IEEE, 2024.
Details
| Link 1