Functionalization via Structure Completion and Motion Rectification

TL;DR

This paper presents a novel approach to transform non-functional 3D models into functional, physically operable ones by completing their structural graphs and rectifying motion errors, using a neural graph-based method.

Contribution

The introduction of object functionalization as a graph completion task and the development of GraFu, a neural graph functionalizer, to enhance 3D model functionality and motion accuracy.

Findings

Achieves state-of-the-art motion prediction accuracy.

Significantly improves model functionality in collision and connectivity metrics.

Introduces FurFun-233 dataset for training and evaluation.

Abstract

Acquisition and creation of 3D assets have been largely view- or appearance-driven. As a result, existing digital 3D models often lack the requisite structural components to function as intended, such as joints, supports, interiors, or interaction elements. At the same time, even human-annotated motions are frequently error-prone, leading to physically implausible behavior. We introduce object functionalization, a novel task aimed at transforming visually plausible but non-functional 3D models into functional and physically operable ones. We formulate functionalization as a graph completion problem over a new functional graph representation, where labeled nodes represent object parts, labeled edges encode functional and contact relations, and movable nodes carry motion attributes, so that structural functional deficiencies manifest as missing nodes or incorrect edges. We develop a neural Graph Functionalizer (GraFu) to complete an incomplete graph representing a non-functional 3D object. The completed graph then drives a geometry realization stage that instantiates predicted connectors and structural elements in 3D, with the compelling side effect of rectifying erroneous human-annotated and predicted motions. To support training and evaluation, focusing on furniture as a rich and challenging target category, we introduce FurFun-233, a dataset of 233 paired non-functional and functionalized furniture models. On PartNet-Mobility ("zero-shot") and HSSD test sets, our method matches state-of-the-art methods in motion prediction accuracy while substantially improving functionality in terms of collision and connectivity.