Applications
ClothCode: Generative Modeling for Garment State Estimation and Dynamics Prediction
arXiv:2610.14200v1 Announce Type: cross Abstract: We introduce ClothCode, a unified generative framework for garment state estimation and action-conditioned dynamics prediction in a shared discrete co
arXiv:2610.14200v1 Announce Type: cross Abstract: We introduce ClothCode, a unified generative framework for garment state estimation and action-conditioned dynamics prediction in a shared discrete configuration space. A material-aligned tokenizer encodes garment configuration as residual vector-quantized patch tokens, while task-specific Masked Generative Transformers predict these tokens through parallel confidence-guided refinement. Across three garment templates, ClothCode reduces mean displacement error by 26.6% for state estimation and 37.0% for dynamics prediction relative to the strongest baselines. Dynamics prediction requires only 16.7 ms per window, compared with 556.2 ms for diffusion. Integrated into the same model-predictive controller, ClothCode improves real-world folding and flattening success from 56.7% to 78.9%. Further results and videos are available at: https://anonymous.4open.science/r/ClothCode-DE32
Related
- DexWorldModel: Causal Latent World Modeling towards Automated Learning of Embodied Tasks
- DyG^2T: Modeling Object Dynamics with 3D Gaussian Temporal-Spatial Particle Graph Transformer
- Lift3D-VLA: Lifting VLA Models to 3D Geometry and Dynamics-Aware Manipulation
Source: arXiv cs.CV | 2026-10-14