Research map / Probabilistic and scientific modeling / Differential equations and PDEs
NTopo: Mesh-free Topology Optimization using Implicit Neural Representations
Jonas Zehnder, Yue Li, Stelian Coros, Bernhard Thomaszewski
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use NTopo (SIREN density/displacement networks) instead of SIMP FEM solver | 2D topology optimization · ShortBeam/LongBeam/Distributed/Bridge | compliance: 4.441 -> 4.385 (Bridge); 1.173e-3 -> 1.166e-3 (ShortBeam) | Improved |
| NTopo versus SIMP runtime | 2D topology optimization · ShortBeam | runtime: 34 s -> 33 min | Hurt |
| replace SIREN with ReLU-MLP density network (ablation) | NTopo · Beam | compliance | Hurt |
| replace SIREN with Fourier feature network (ablation) | NTopo · Beam | compliance: 0.001172 | No clear effect |
| remove sensitivity filtering (ablation) | NTopo · Beam | design quality | Hurt |
| remove moving MSE and optimality criterion (direct density-gradient update with volume penalty) (ablation) | NTopo · Beam | design quality | Hurt |
| self-supervised moving-MSE training instead of supervised training on 11 solutions | solution-space network · unseen volume constraints | design validity | Improved |
Closest papers by meaning
- Optimize Any Topology: A Foundation Model for Shape- and Resolution-Free Structural Topology Optimization (NeurIPS 2025 · similarity 0.86)
- Better Neural PDE Solvers Through Data-Free Mesh Movers (ICLR 2024 · similarity 0.85)
- Diffeomorphic interpolation for efficient persistence-based topological optimization (NeurIPS 2024 · similarity 0.85)
- Reference Neural Operators: Learning the Smooth Dependence of Solutions of PDEs on Geometric Deformations (ICML 2024 · similarity 0.85)
- Feature-Mapping Topology Optimization with Neural Heaviside Signed Distance Functions (ICML 2025 · similarity 0.85)
- Interpolating Neural Network-Tensor Decomposition (INN-TD): a scalable and interpretable approach for large-scale physics-based problems (ICML 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
