Research map / 3D vision / 3D generation
Few-Shot Physically-Aware Articulated Mesh Generation via Hierarchical Deformation
Xueyi Liu, Bin Wang, He Wang, Li Yi
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| replace part-level deformation with hierarchical convex-level deformation (ablation) | Ours · PartNet-Mobility avg | COV (%): 36.41 -> 50.45 | Improved |
| add transfer learning from rigid meshes (ablation) | Ours · PartNet-Mobility avg | COV (%): 46.64 -> 50.45 | Improved |
| add fine-tuning on target articulated data after pre-training (ablation) | Ours · PartNet-Mobility avg | MMD (x10^3): 6.538 -> 5.198 | Improved |
| use half the rigid pre-training data (ablation) | Ours · PartNet-Mobility avg | MMD (x10^3): 5.201 vs 5.198 | No clear effect |
| add physical supervision and shape optimization (ablation) | Ours · PartNet-Mobility avg | APD (x10^2): 1.8079 -> 1.3192 | Improved |
| add test-time adaptation shape optimization (ablation) | Ours · PartNet-Mobility avg | APD (x10^2): 1.6443 -> 1.3192 | Improved |
| add physics-aware correction to DeepMetaHandles (ablation) | DeepMetaHandles · PartNet-Mobility avg | APD (x10^2): 1.7955 -> 1.5705 | Improved |
| use Ours instead of PolyGen | few-shot articulated mesh generation · PartNet-Mobility avg | APD (x10^2): 1.0068 -> 1.3192 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- DeepMetaHandles — DeepMetaHandles: Learning Deformation Meta-Handles of 3D Meshes With Biharmonic Coordinates (CVPR 2021) · better on 5 of 5 shared results
- PolyGen — PolyGen: An Autoregressive Generative Model of 3D Meshes (ICML 2020) · better on 2 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- MeshArt: Generating Articulated Meshes with Structure-Guided Transformers (CVPR 2025 · similarity 0.90)
- SINGAPO: Single Image Controlled Generation of Articulated Parts in Objects (ICLR 2025 · similarity 0.88)
- MIDGArD: Modular Interpretable Diffusion over Graphs for Articulated Designs (NeurIPS 2024 · similarity 0.87)
- ArtFormer: Controllable Generation of Diverse 3D Articulated Objects (CVPR 2025 · similarity 0.87)
- ARMesh: Autoregressive Mesh Generation via Next-Level-of-Detail Prediction (NeurIPS 2025 · similarity 0.87)
- CAGE: Controllable Articulation GEneration (CVPR 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
