GRAFT: Graph-Based Affordance Transfer via Part Correspondence

Mengying Lin, Utkarsh Mishra, Ajay Mandlekar, Danfei Xu; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Findings, 2026, pp. 8746-8755

Generalizing robotic manipulation to unseen objects remains challenging, as learning-based approaches require many demonstrations and fail in few-shot settings. Prior work transfers affordances through semantic retrieval, but semantics alone neglect geometric similarity, which is critical for manipulation. We propose GRAFT, a geometry-aware correspondence framework for zero-shot manipulation transfer using only one demonstration per object. Objects are represented as part-based graphs, where part-level descriptors support global instance retrieval and part correspondence, and vertex-level descriptors enable fine-grained contact point matching. For an unseen object, our method first retrieves the most functionally and geometrically similar instance from the demonstration buffer with aligned functional parts, and finally propagates the contact points through point-wise correspondence. GRAFT enables zero-shot manipulation transfer through structure-driven correspondence and supports scalable, physically valid demonstration generation via MimicGen. Across zero-shot affordance, physics-based simulation, and real-world evaluations, GRAFT achieves substantially higher correspondence accuracy, manipulation success, and retrieval diversity.