MonoArt: Progressive Structural Reasoning for Monocular Articulated 3D Reconstruction
This work solves the challenge of monocular articulated 3D reconstruction for applications like robotics and scene understanding, representing an incremental improvement over existing methods.
The paper tackles the problem of reconstructing articulated 3D objects from a single image by addressing the entanglement between motion and structure, resulting in state-of-the-art performance in accuracy and speed on the PartNet-Mobility dataset.
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.