Research map / Probabilistic and scientific modeling / Molecules and proteins
Planar Symmetric Pattern Generation
Ning Lin, Luxi Chen, Huaguan Chen, Jiacheng Cen, Chongxuan Li, Wenbing Huang, Hao Sun
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 proposed symmetric continuous representation instead of basis projection (alpha=0.25) | SD 2.1 p1 pattern generation · p1 pattern (n=128) | CLIP-A: 3.07 -> 4.20 | Improved |
| use proposed representation instead of basis projection (alpha=1.00) | SD 2.1 p1 pattern generation · p1 pattern (n=256) | CLIP-A: 3.48 -> 3.99 | Improved |
| use proposed representation instead of basis projection (alpha=1.00) | SD 2.1 p1 pattern generation · p1 pattern (n=64) | CLIP-A: 4.05 -> 4.30 | Improved |
| enforce symmetry by post-symmetrization instead of generating in symmetric representation | GPT-5.2 and Gemini 3 Pro · 17-prompt pattern design | CLIP-A | Hurt |
| use SDS on symmetric representation instead of CLIP loss baseline | topology design · variable angle p1 (CLIP-A and bulk modulus) | CLIP-A and bulk modulus | Mixed |
| use SDS on symmetric representation instead of CLIP baseline for p2 and pm groups | topology design · variable symmetry | CLIP-A and bulk modulus | Improved |
Closest papers by meaning
- Generating Symmetric Materials using Latent Flow Matching (NeurIPS 2026 · similarity 0.83)
- Learning Infinitesimal Generators of Continuous Symmetries from Data (NeurIPS 2024 · similarity 0.82)
- Space Group Conditional Flow Matching (NeurIPS 2026 · similarity 0.82)
- A Generative Model of Symmetry Transformations (NeurIPS 2024 · similarity 0.82)
- Symmetry Strikes Back: From Single-Image Symmetry Detection to 3D Generation (CVPR 2025 · similarity 0.81)
- SymmCD: Symmetry-Preserving Crystal Generation with Diffusion Models (ICLR 2025 · similarity 0.81)
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.
