Research map / Image generation / GANs
Diffusion Models Beat GANs on Topology Optimization
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Replace TopologyGAN with guided TopoDiff | Topology optimization · Level 1 test data | Average compliance error (%): 48.51 ± 16.38 -> 4.39 ± 0.94 | Helped |
| Replace TopologyGAN with guided TopoDiff | Topology optimization · Level 2 test data | Average compliance error (%): 143.08 ± 38.50 -> 18.40 ± 5.88 | Helped |
| Replace TopologyGAN with guided TopoDiff | Topology optimization · Level 1 test data | Proportion of floating material (%): 46.78 -> 5.54 | Helped |
| Replace TopologyGAN with guided TopoDiff | Topology optimization · Level 2 test data | Proportion of floating material (%): 67.90 -> 6.21 | Helped |
| Add compliance and floating-material guidance (ablation) | TopoDiff · Level 1 test data | Average compliance error (%): 4.10 ± 0.88 -> 4.39 ± 0.94 | No clear effect |
| Add compliance and floating-material guidance (ablation) | TopoDiff · Level 1 test data | Proportion of floating material (%): 6.64 -> 5.54 | Helped |
| Add compliance and floating-material guidance (ablation) | TopoDiff · Level 2 test data | Average compliance error (%): 22.13 ± 8.52 -> 18.40 ± 5.88 | Helped |
| Add compliance and floating-material guidance (ablation) | TopoDiff · Level 2 test data | Proportion of floating material (%): 7.53 -> 6.21 | Helped |
| Add compliance and floating-material guidance (ablation) | TopoDiff · Level 2 test data | Median compliance error (%): 1.88 -> 1.82 | No clear effect |
Closest papers by meaning
- Optimize Any Topology: A Foundation Model for Shape- and Resolution-Free Structural Topology Optimization (NeurIPS 2025 · similarity 0.88)
- CcDPM: A Continuous Conditional Diffusion Probabilistic Model for Inverse Design (AAAI 2024 · similarity 0.87)
- TopoDiffusionNet: A Topology-aware Diffusion Model (ICLR 2025 · similarity 0.86)
- Feature-Mapping Topology Optimization with Neural Heaviside Signed Distance Functions (ICML 2025 · similarity 0.84)
- Diffusion-Based Hierarchical Graph Neural Networks for Simulating Nonlinear Solid Mechanics (NeurIPS 2025 · similarity 0.84)
- Discovering Phase Space Structure in Learned Hamiltonian Systems (NeurIPS 2026 · similarity 0.83)
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.