Research map / Graph learning / GNN architectures
HOOD: Hierarchical Graphs for Generalized Modelling of Clothing Dynamics
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 single-level 15-step message passing with hierarchical message passing (ablation) | HOOD · VTO dress (12K vertices) | total loss: 2.92 -> 1.48 | Helped |
| replace single-level 15-step message passing with hierarchical message passing (ablation) | HOOD · VTO dress (12K vertices) | average speed (fps): 6.65 -> 7.27 | Helped |
| replace single-level 15-step message passing with hierarchical message passing (ablation) | HOOD · validation set (all garments) | total loss: 1.68 -> 1.07 | Helped |
| replace single-level 15-step message passing with hierarchical message passing (ablation) | HOOD · validation set (all garments) | average speed (fps): 13.1 -> 13.6 | Helped |
| replace hierarchical message passing with single-level 48-step message passing (ablation) | HOOD · VTO dress (12K vertices) | average speed (fps): 7.27 -> 2.45 | Hurt |
| replace hierarchical message passing with single-level 48-step message passing (ablation) | HOOD · VTO dress (12K vertices) | total loss: 1.48 -> 1.43 | Helped |
| replace hierarchical message passing with single-level 48-step message passing (ablation) | HOOD · validation set (all garments) | average speed (fps): 13.6 -> 4.99 | Hurt |
| replace hierarchical message passing with single-level 48-step message passing (ablation) | HOOD · validation set (all garments) | total loss: 1.07 -> 1.04 | Helped |
| increase single-level message passing from 15 to 48 steps (ablation) | HOOD · VTO dress (12K vertices) | average speed (fps): 6.65 -> 2.45 | Hurt |
| increase single-level message passing from 15 to 48 steps (ablation) | HOOD · validation set (all garments) | average speed (fps): 13.1 -> 4.99 | Hurt |
Closest papers by meaning
- Learning 3D Garment Animation from Trajectories of A Piece of Cloth (NeurIPS 2024 · similarity 0.88)
- Garment Recovery with Shape and Deformation Priors (CVPR 2024 · similarity 0.87)
- GarFast: Realistic and Fast Garment Transfer with a Simplified Parser-Free Approach (AAAI 2025 · similarity 0.86)
- NeuralClothSim: Neural Deformation Fields Meet the Thin Shell Theory (NeurIPS 2024 · similarity 0.86)
- AnyDressing: Customizable Multi-Garment Virtual Dressing via Latent Diffusion Models (CVPR 2025 · similarity 0.86)
- FreeCloth: Free-form Generation Enhances Challenging Clothed Human Modeling (CVPR 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.