Presentation

<
MIND: Microstructure INverse Design with Generative Hybrid Neural Representation
SessionMicrostructures & Materials
DescriptionWe introduce MIND, a novel generative framework for inverse-designing diverse, tileable 3D microstructures. Leveraging latent diffusion and our hybrid neural representation, MIND precisely achieves targeted physical properties, ensures geometric validity, and enables seamless boundary compatibility—opening new avenues for advanced metamaterial design and manufacturing applications.
Authors
Tianyang Xue
Shandong University
Longdu Liu
Shandong University
Lin Lu
Shandong University
Paul Henderson
University of Glasgow
Pengbin Tang
ETH Zürich
Haochen Li
Shandong University
Jikai Liu
Shandong University
Haisen Zhao
Shandong University
Hao Peng
CrownCAD
Bernd Bickel
ETH Zürich
Event Type
Technical Paper
TimeWednesday, 13 August 20253:45pm - 3:55pm PDT
LocationWest Building, Rooms 211-214
ACM Digital Library Journal Papers' PDFs
Conference Papers' PDFs
Session Time & Location
Sunday, 10 August 20256:00pm - 8:45pm PDTWest Building, Ballroom AB
Wednesday, 13 August 20253:45pm - 5:35pm PDTWest Building, Rooms 211-214
Interest Areas
Research & Education
Recordings
Livestreamed
Recorded
Registration Categories
Full Conference
Virtual Access
Wednesday
Next PresentationNext PresentationNeural Co-Optimization of Structural Topology, Manufacturable Layers, and Path Orientations for Fiber-Reinforced Composites
Similar Presentations
Inverse Design of Discrete Interlocking Materials with Desired Mechanical Behavior
DeepMill: Neural Accessibility Learning for Subtractive Manufacturing
HoLa: B-Rep Generation using a Holistic Latent Representation