Functionalization via Structure Completion and Motion Rectification

• URL: http://arxiv.org/abs/2605.18010v1
• Date: Mon, 18 May 2026 08:05:07 GMT
• Title: Functionalization via Structure Completion and Motion Rectification
• Abstract summary: We introduce object functionalization, a novel task aimed at transforming visually plausible but non-functional 3D models into functional and physically operable ones.<n>We develop a neural Graph Functionalizer (GraFu) to complete an incomplete graph representing a non-functional 3D object.<n>The completed graph then drives a geometry realization stage that instantiates predicted connectors and structural elements in 3D.
• Score: 44.37223222305385
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• PhysGraph: A Physics-aware 3D Scene Graph for Perception and Reasoning [24.361346589238035]
  We present PhysGraph, a framework that unifies symbolic reasoning with structured 3D geometry to model kinematic and physical properties in cluttered scenes.<n> PhysGraph achieves state-of-the-art results in semantic segmentation, multi-object mass estimation, and articulation prediction.
  arXiv  Detail & Related papers  (2026-06-07T14:50:44Z)
• Hierarchical and Holistic Open-Vocabulary Functional 3D Scene Graphs for Indoor Spaces [116.57196064763924]
  We extend the benchmark coverage by introducing dense tabletop objects and explicit multi-level functional relationships.<n>This work introduces critical challenges involving small-scale, dense, and similar instances.<n>We propose an open-vocabulary pipeline based on 2D visual grounding and 3D graph optimization.
  arXiv  Detail & Related papers  (2026-05-15T09:14:50Z)
• EgoFun3D: Modeling Interactive Objects from Egocentric Videos using Function Templates [10.36299959288067]
  We present EgoFun3D, a coordinated task formulation, dataset, and benchmark for modeling interactive 3D objects from egocentric videos.<n>Our task focuses on obtaining simulation-ready interactive 3D objects from egocentric video input.<n>To tackle the task, we propose a 4-stage pipeline consisting of: 2D part segmentation, reconstruction, articulation estimation, and function template inference.
  arXiv  Detail & Related papers  (2026-04-13T06:06:23Z)
• From Perception to Action: An Interactive Benchmark for Vision Reasoning [51.11355591375073]
  Causal Hierarchy of Actions and Interactions (CHAIN) benchmark designed to evaluate whether models can understand, plan, and execute structured action sequences grounded in physical constraints.<n> CHAIN shifts evaluation from passive perception to active problem solving, spanning tasks such as interlocking mechanical puzzles and 3D stacking and packing.<n>Our results show that top-performing models still struggle to internalize physical structure and causal constraints, often failing to produce reliable long-horizon plans and cannot robustly translate perceived structure into effective actions.
  arXiv  Detail & Related papers  (2026-02-24T15:33:02Z)
• ArtiSG: Functional 3D Scene Graph Construction via Human-demonstrated Articulated Objects Manipulation [51.54082859171464]
  ArtiSG is a framework that constructs functional 3D scene graphs by encoding human demonstrations into structured robotic memory.<n>We show that ArtiSG significantly outperforms baselines in functional element recall and articulation estimation precision.
  arXiv  Detail & Related papers  (2025-12-31T13:10:40Z)
• Self-Supervised Multi-Part Articulated Objects Modeling via Deformable Gaussian Splatting and Progressive Primitive Segmentation [23.18517560629462]
  We introduce DeGSS, a unified framework that encodes articulated objects as deformable 3D Gaussian fields, embedding geometry, appearance, and motion in one compact representation.<n>To evaluate generalization and realism, we enlarge the synthetic PartNet-Mobility benchmark and release RS-Art, a real-to-sim dataset that pairs RGB captures with accurately reverse-engineered 3D models.
  arXiv  Detail & Related papers  (2025-06-11T12:32:16Z)
• Semi-Weakly Supervised Object Kinematic Motion Prediction [56.282759127180306]
  Given a 3D object, kinematic motion prediction aims to identify the mobile parts as well as the corresponding motion parameters. We propose a graph neural network to learn the map between hierarchical part-level segmentation and mobile parts parameters. The network predictions yield a large scale of 3D objects with pseudo labeled mobility information.
  arXiv  Detail & Related papers  (2023-03-31T02:37:36Z)
• Fixing Malfunctional Objects With Learned Physical Simulation and Functional Prediction [158.74130075865835]
  Given a malfunctional 3D object, humans can perform mental simulations to reason about its functionality and figure out how to fix it. To mimic humans' mental simulation process, we present FixNet, a novel framework that seamlessly incorporates perception and physical dynamics.
  arXiv  Detail & Related papers  (2022-05-05T17:59:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.