[Paper] Synthetic Data Generation and Vision-based Wrinkle and Keypoint Detection for Bimanual Cloth Manipulation
Source: arXiv - 2606.06292v1
Overview
Robotic manipulation of textiles remains challenging because continuous deformation and self‑occlusions hinder the robust visual perception required to estimate the cloth’s state. To address the lack of annotated real‑world data, we developed a Blender‑based synthetic pipeline exporting auto‑annotated keypoints, and combined manually labeled renders with real‑world data to train a wrinkle detector. We present a perception framework integrating a CNN for permutation‑invariant keypoint detection and a YOLOv8‑OpenCV pipeline to extract grasping points from structural wrinkles. A proposed bimanual algorithm uses this system to stretch fully folded garments via wrinkles, transitioning to keypoint‑based ironing once corners emerge. The keypoint model achieves a Mean Position Error (MPE) of 1.7615 pixels. The perception system transfers to physical fabrics without fine‑tuning, outperforming baselines that fail in high‑occlusion states or yield false positives on severe folds.
Key Contributions
- cs.CV
- cs.RO
Methodology
Please refer to the full paper for detailed methodology.
Practical Implications
This research contributes to the advancement of cs.CV.
Authors
- Ariel Herrera
- Xueyang Kang
- Atal Anil Kumar
Paper Information
- arXiv ID: 2606.06292v1
- Categories: cs.CV, cs.RO
- Published: June 4, 2026
- PDF: Download PDF