GarmentTracking: Category-Level Garment Pose Tracking
This work addresses garment pose tracking for applications in robotics and virtual reality, presenting a complete package including dataset and framework, but it is incremental as it builds on existing tracking methods.
The authors tackled the problem of category-level garment pose tracking by introducing a VR recording system, a large-scale dataset, and an end-to-end tracking framework, achieving great performance with large non-rigid deformations and outperforming baselines in speed and accuracy.
Garments are important to humans. A visual system that can estimate and track the complete garment pose can be useful for many downstream tasks and real-world applications. In this work, we present a complete package to address the category-level garment pose tracking task: (1) A recording system VR-Garment, with which users can manipulate virtual garment models in simulation through a VR interface. (2) A large-scale dataset VR-Folding, with complex garment pose configurations in manipulation like flattening and folding. (3) An end-to-end online tracking framework GarmentTracking, which predicts complete garment pose both in canonical space and task space given a point cloud sequence. Extensive experiments demonstrate that the proposed GarmentTracking achieves great performance even when the garment has large non-rigid deformation. It outperforms the baseline approach on both speed and accuracy. We hope our proposed solution can serve as a platform for future research. Codes and datasets are available in https://garment-tracking.robotflow.ai.