Research map / Graph learning / GNN architectures
Pb4U-GNet: Resolution-Adaptive Garment Simulation via Propagation-before-Update Graph Network
Aoran Liu, Kun Hu, Clinton Ansun Mo, Qiuxia Wu, Wenxiong Kang, Zhiyong Wang
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 |
|---|---|---|---|
| add resolution-aware propagation control (adaptive message-passing steps) (ablation) | Pb4U-GNet · VTO Lv.4 (38K), trained on 11K only | total physics loss: 1.08E+09 -> 2.22E-01 | Improved |
| add resolution-aware update scaling (ablation) | Pb4U-GNet · VTO Lv.4 (38K), trained on 11K only | total physics loss: 7.34E+13 -> 2.22E-01 | Improved |
| add propagation control at training resolution (ablation) | Pb4U-GNet · VTO Lv.1 (11K) | total physics loss: -1.61E-03 (w/o) vs -1.66E-02 | No clear effect |
| use update scaling at training resolution (ablation) | Pb4U-GNet · VTO Lv.1 (11K) | total physics loss: -5.78E-03 (w/o) vs -1.66E-02 | No clear effect |
| use Pb4U-GNet vs baselines at unseen higher resolutions | Pb4U-GNet · VTO Lv.4 (38K) | total physics loss: 2.82E-01 (CCRAFT) -> 2.22E-01 | Improved |
| use Pb4U-GNet at training resolution | Pb4U-GNet · VTO Lv.1 (11K) | total physics loss: -1.66E-02 vs ESLR -2.56E-02 | No clear effect |
| adaptive propagation steps on low-resolution mesh | Pb4U-GNet · VTO 12K dress | latency (ms): 50.0 ms vs MGN 46.4 ms, HOOD 50.8 ms | No clear effect |
| generalize to unseen garment types (dress and cardigan) | Pb4U-GNet · VTO unseen garments, highest resolution | total physics loss: 2.64E-01 (CCRAFT) -> 1.55E-01 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- HOOD — HOOD: Hierarchical Graphs for Generalized Modelling of Clothing Dynamics (CVPR 2023) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- NeuralGarSim: Geometry-agnostic Garment Simulation with Neural Fields (ECCV 2026 · similarity 0.87)
- Spectrum-Enhanced Graph Attention Network for Garment Mesh Deformation (TPAMI 2025 · similarity 0.87)
- HOOD: Hierarchical Graphs for Generalized Modelling of Clothing Dynamics (CVPR 2023 · similarity 0.87)
- GarNet: A Two-Stream Network for Fast and Accurate 3D Cloth Draping (ICCV 2019 · similarity 0.87)
- GarFast: Realistic and Fast Garment Transfer with a Simplified Parser-Free Approach (AAAI 2025 · similarity 0.85)
- Learning 3D Garment Animation from Trajectories of A Piece of Cloth (NeurIPS 2024 · 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.
