Research map / 3D vision / Human pose estimation
GarmentTracking: Category-Level Garment Pose Tracking
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 |
|---|---|---|---|
| Use online inter-frame garment tracking rather than frame-by-frame GarmentNets prediction | GarmentTracking · VR-Folding folding and flattening across four categories | A3cm (folding) and A5cm (flattening): 0.8% -> 29.8% (Shirt Folding); 1.5% -> 31.3% (Pants Flattening) | Helped |
| Perturb first-frame pose and canonical-shape initialization | GarmentTracking · VR-Folding | A3cm (folding) and A5cm (flattening): 29.8% -> 29.0% (Shirt Folding); 30.7% -> 25.4% (Shirt Flattening) | Mixed |
| Add NOCS positional embedding from the previous frame (ablation) | GarmentTracking · VR-Folding garment tracking | canonical-coordinate prediction | Helped |
| Add the PC refiner to refine per-frame NOCS predictions (ablation) | GarmentTracking · VR-Folding Shirt and Pants Folding | A3cm: 4.1% -> 29.0% (Shirt); 23.1% -> 42.8% (Pants) | Helped |
| Add the Mesh refiner (ablation) | GarmentTracking · VR-Folding Shirt and Pants Folding | A3cm: 26.8% -> 29.0% (Shirt); 33.5% -> 42.8% (Pants) | Helped |
| Replace PointNet++ with the ResUNet3D sparse 3D-convolution feature extractor (ablation) | GarmentTracking · VR-Folding Shirt and Pants Folding | A3cm: 2.2% -> 29.0% (Shirt); 8.9% -> 42.8% (Pants) | Helped |
| Use ResUNet3D rather than PointNet++ (ablation) | GarmentTracking · VR-Folding flattening | A5cm: 13.3% -> 25.4% (Shirt); 8.0% -> 30.7% (Pants) | Helped |
| Use the full tracking method rather than GarmentNets | GarmentTracking · VR-Folding Pants Folding | Dnocs: 0.162 -> 0.039 | Helped |
| Use the full tracking method rather than GarmentNets | GarmentTracking · VR-Folding Shirt Folding | speed: 3.6 FPS -> 15 FPS | Helped |
| Use GarmentNets predictions as the first-frame pose | GarmentTracking · VR-Folding Folding | A3cm: 0.8% -> 25.4% (Shirt); 16.2% -> 45.1% (Pants) | Helped |
Closest papers by meaning
- GaPT-DAR: Category-level Garments Pose Tracking via Integrated 2D Deformation and 3D Reconstruction (CVPR 2025 · similarity 0.92)
- GarmentLab: A Unified Simulation and Benchmark for Garment Manipulation (NeurIPS 2024 · similarity 0.88)
- Incorporating Visual Correspondence into Diffusion Model for Virtual Try-On (ICLR 2025 · similarity 0.87)
- DexGarmentLab: Dexterous Garment Manipulation Environment with Generalizable Policy (NeurIPS 2025 · similarity 0.87)
- GarmentPile: Point-Level Visual Affordance Guided Retrieval and Adaptation for Cluttered Garments Manipulation (CVPR 2025 · similarity 0.87)
- Learning Efficient Robotic Garment Manipulation with Standardization (ICML 2025 · similarity 0.86)
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.