Spatial and Surface Correspondence Field for Interaction Transfer

TL;DR

This paper presents a novel method for interaction transfer that leverages a combined spatial and surface correspondence field to improve transfer accuracy across varied geometries.

Contribution

It introduces a new approach using a learned correspondence field with deformed signed distance fields for more accurate interaction transfer.

Findings

Outperforms state-of-the-art methods on human-chair and hand-mug tasks.

Handles larger geometry and topology variations effectively.

Provides more accurate and valid interaction transfers.

Abstract

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.