MonoArt: Progressive Structural Reasoning for Monocular Articulated 3D Reconstruction

2026-03-19

AI Summary

Reconstructing the 3D structure of articulated objects from a single image requires joint inference of geometry, part hierarchy, and motion parameters; however, the tight coupling between motion and structure often leads to unstable regression. This work proposes MonoArt, the first unified framework enabling end-to-end, progressive joint reasoning of structure and motion, eliminating the need for multi-stage pipelines or external motion templates. Within a single architecture, MonoArt sequentially generates canonical geometry, structured part representations, and motion-aware embeddings, achieving stable and interpretable reconstruction. The method attains state-of-the-art accuracy and speed on PartNet-Mobility and demonstrates successful generalization to robotic manipulation tasks and real-world articulated scene reconstruction.

Technology Category

• Computer Vision: Motion & Tracking
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Intelligent Robots: Motion and Path Planning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Reconstructing articulated 3D objects from a single image requires jointly inferring object geometry, part structure, and motion parameters from limited visual evidence. A key difficulty lies in the entanglement between motion cues and object structure, which makes direct articulation regression unstable. Existing methods address this challenge through multi-view supervision, retrieval-based assembly, or auxiliary video generation, often sacrificing scalability or efficiency. We present MonoArt, a unified framework grounded in progressive structural reasoning. Rather than predicting articulation directly from image features, MonoArt progressively transforms visual observations into canonical geometry, structured part representations, and motion-aware embeddings within a single architecture. This structured reasoning process enables stable and interpretable articulation inference without external motion templates or multi-stage pipelines. Extensive experiments on PartNet-Mobility demonstrate that OM achieves state-of-the-art performance in both reconstruction accuracy and inference speed. The framework further generalizes to robotic manipulation and articulated scene reconstruction.

Problem

• monocular 3D reconstruction
• articulated objects
• structural reasoning
• motion-structure entanglement
• single-image inference

Innovation

• progressive structural reasoning
• monocular articulated 3D reconstruction
• motion-aware embedding
• canonical geometry
• structured part representation