PAct: Part-Decomposed Single-View Articulated Object Generation

2026-02-16

AI Summary

Existing methods for generating high-fidelity articulated 3D objects struggle to simultaneously achieve structural accuracy, motion plausibility, and inference efficiency, often relying on time-consuming optimization or template matching. This work proposes a part-centric generative framework that, for the first time, explicitly incorporates part identity and motion cues into an end-to-end generation pipeline. The approach synthesizes 3D articulated objects directly from a single image—without per-instance optimization—yielding explicit part decomposition, coherent geometry, and physically plausible kinematic relationships. By leveraging a part-aware implicit token representation, the model jointly encodes geometric, compositional, and motion constraints, enabling fast feed-forward inference and controllable assembly. Evaluated on categories such as drawers and doors, the method significantly outperforms optimization- and retrieval-based baselines, demonstrating marked improvements in input consistency, part accuracy, motion plausibility, and inference speed.

Technology Category

• Computer Vision: Motion & Tracking
• Natural Language Processing: Generation
• Machine Learning: Deep Generative Models & Autoencoders

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Articulated objects are central to interactive 3D applications, including embodied AI, robotics, and VR/AR, where functional part decomposition and kinematic motion are essential. Yet producing high-fidelity articulated assets remains difficult to scale because it requires reliable part decomposition and kinematic rigging. Existing approaches largely fall into two paradigms: optimization-based reconstruction or distillation, which can be accurate but often takes tens of minutes to hours per instance, and inference-time methods that rely on template or part retrieval, producing plausible results that may not match the specific structure and appearance in the input observation. We introduce a part-centric generative framework for articulated object creation that synthesizes part geometry, composition, and articulation under explicit part-aware conditioning. Our representation models an object as a set of movable parts, each encoded by latent tokens augmented with part identity and articulation cues. Conditioned on a single image, the model generates articulated 3D assets that preserve instance-level correspondence while maintaining valid part structure and motion. The resulting approach avoids per-instance optimization, enables fast feed-forward inference, and supports controllable assembly and articulation, which are important for embodied interaction. Experiments on common articulated categories (e.g., drawers and doors) show improved input consistency, part accuracy, and articulation plausibility over optimization-based and retrieval-driven baselines, while substantially reducing inference time.

Problem

• articulated object generation
• part decomposition
• single-view reconstruction
• kinematic motion
• 3D asset creation

Innovation

• part-decomposed generation
• articulated object modeling
• single-view 3D reconstruction
• latent token representation
• feed-forward inference