Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

MonoArt: Progressive Structural Reasoning for Monocular Articulated 3D Reconstruction

Haitian Li, Haozhe Xie, Junxiang Xu, Beichen Wen, Fangzhou Hong, Ziwei Liu

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.

MonoArt: Progressive Structural Reasoning for Monocular Articulated 3D Reconstruction

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.
Paper Structure (54 sections, 24 equations, 10 figures, 4 tables)

This paper contains 54 sections, 24 equations, 10 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Articulated Object Modeling
  4. 3D Part Segmentation
  5. Our Approach
  6. Overview
  7. TRELLIS-based 3D Generator
  8. Part-Aware Semantic Reasoner
  9. Tri-linear Interpolation
  10. Triplane Projection
  11. Part Contrast Transformer
  12. Dual-Query Motion Decoder
  13. Dual-query Initialization
  14. Refinement Block
  15. Query Confidence Estimation
  16. ...and 39 more sections

Figures (10)

  • Figure 1: (Left) Qualitative results of SINGAPO DBLP:conf/iclr/LiuICSA25, Articulate-Anything (ArtAny) DBLP:conf/iclr/LeXLWYMVKJE25, PhysX-Anything (PhysXAny) DBLP:journals/corr/abs-2511-13648, and MonoArt on diverse objects. (Right) F-score vs. inference time on the PartNet-Mobility DBLP:conf/cvpr/XiangQMXZLLJYWY20 test set. Circles indicate models evaluated on 7 categories, while triangles denote models supporting all 46 categories.
  • Figure 2: Overview of MonoArt. TRELLIS-based 3D Generator reconstructs a canonical shape from a single image. Part-Aware Semantic Reasoner derives tri-plane-based part embeddings. Dual-Query Motion Decoder performs iterative motion reasoning, and Kinematic Estimator predicts part-level articulation parameters (motion type, origin, axis, limits) and infers the kinematic tree structure. Note that "Attn.", "Interp.", "Proj.", "Cont.", "Trans.", and "Init." represent "Attention", "Interpolation", "Projection", "Contrast", "Transformer", and "Initialization", respectively. $\oplus$ and $\otimes$ denote element-wise addition and matrix multiplication, respectively.
  • Figure 3: Qualitative results on the test set of PartNet-Mobility. ArtAny and PhysXAny denote Articulate-Anything and PhysXAnything, respectively. For each object, we show the reconstructed geometry under two sampled articulated states.
  • Figure 4: Qualitative results on in-the-wild images. ArtAny and PhysXAny denote Articulate-Anything and PhysXAnything, respectively. For each object, we show the reconstructed geometry under two sampled articulated states.
  • Figure 5: Robot manipulation with generated articulated objects. MonoArt reconstructions are directly imported into IsaacSim for contact-rich interaction.
  • ...and 5 more figures