Spatial and Surface Correspondence Field for Interaction Transfer
This addresses interaction transfer for computer graphics or robotics applications, but appears incremental as it builds on existing representation and optimization techniques.
The paper tackles the problem of transferring interactions between objects and agents by introducing a method that infers spatial and surface relationships, achieving more accurate transfers. Experiments on human-chair and hand-mug tasks show it handles larger geometry variations and significantly outperforms state-of-the-art methods.
In this paper, we introduce a new method for the task of interaction transfer. Given an example interaction between a source object and an agent, our method can automatically infer both surface and spatial relationships for the agent and target objects within the same category, yielding more accurate and valid transfers. Specifically, our method characterizes the example interaction using a combined spatial and surface representation. We correspond the agent points and object points related to the representation to the target object space using a learned spatial and surface correspondence field, which represents objects as deformed and rotated signed distance fields. With the corresponded points, an optimization is performed under the constraints of our spatial and surface interaction representation and additional regularization. Experiments conducted on human-chair and hand-mug interaction transfer tasks show that our approach can handle larger geometry and topology variations between source and target shapes, significantly outperforming state-of-the-art methods.