MidSurfNet: Learnable Face Pairing and Interference Implicit Fields for Generalized Mid-surface Abstraction
2026-06-01 • Graphics
GraphicsMachine Learning
AI summaryⓘ
The authors created MidSurfNet, a new method to find the middle surface of thin 3D CAD models, which is important for engineering simulations. Unlike older rule-based methods, their approach uses a neural network to better match faces, even in tricky cases like multiple wall thicknesses or faces that look similar. They also introduced a special mathematical way to control the position of these middle surfaces precisely. Testing on over 1,500 models showed their method works much better than existing ones, especially in difficult scenarios. This helps make simulations more accurate and flexible for real-world designs.
Mid-surface abstractionFinite Element Analysis (FEA)CAD modelsNeural face pairingSigned distance functionMulti-wall-thicknessSelf-matching facesInterference implicit fieldOffset controlCAE workflows
Authors
Li Ye, Xinhang Zhou, Xingyu Yang, Ruofeng Tong, Hailong Li, Peng Du, Min Tang
Abstract
Mid-surface abstraction is essential for finite element analysis of thin-walled CAD models. Existing face pairing-based methods rely on handcrafted geometric heuristics, yet real-world industrial models frequently exhibit multi-wall-thickness regions, self-matching face configurations, and demand for non-center offset surfaces--scenarios where rule-based approaches consistently fail. We present MidSurfNet, a learning-augmented framework that addresses these limitations through two novel components: (1) a neural face pairing module that learns to predict face pair confidence from geometric and topological features, handling complex pairing scenarios beyond rule-based methods; and (2) an interference implicit field that represents mid-surfaces as the interference of two signed distance functions, enabling generalized offset control for flexible positioning in downstream CAE/FEA-oriented workflows. We construct a large-scale mid-surface dataset containing over 1,500 manually annotated CAD models. Experiments demonstrate that MidSurfNet achieves 87.32% face pairing accuracy and successfully handles multi-wall-thickness (61.90% completion) and self-matching (52.94% completion) scenarios that confound all existing methods. Furthermore, MidSurfNet provides a learning-based approach to generalized mid-surface abstraction with arbitrary offset control for CAE-oriented applications.