Research map / 3D vision / 3D generation
ARMO: Autoregressive Rigging for Multi-Category Objects
Mingze Sun, Shiwei Mao, Keyi Chen, Yurun Chen, Shunlin Lu, Jingbo Wang, Junting Dong, Ruqi Huang
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 multi-stage regression with MST by an autoregressive joint-and-parent model | ARMO · OmniRig test set | IoU: 61.35% -> 70.68% | Improved |
| predict joints and parents autoregressively instead of MST connectivity | ARMO · OmniRig test set | CD-B2B: 5.06% -> 2.95% | Improved |
| add autoregressive auto-encoder plus latent diffusion rather than direct point cloud diffusion with MST (ablation) | ARMO · OmniRig test set | CD-B2B: 6.31% -> 2.95% | Improved |
| use latent diffusion conditioning instead of a GPT-based conditioned autoregressive model (ablation) | ARMO · OmniRig test set | CD-J2J: 5.20% -> 3.88% | Improved |
| add online pose augmentation during training (ablation) | ARMO · OmniRig test set | CD-J2J: 4.04% -> 3.88% | Improved |
| add online pose augmentation during training (ablation) | ARMO · OmniRig test set | IoU: 66.79% -> 70.68% | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- RigNet — RigNet: Repetitive Image Guided Network for Depth Completion (ECCV 2022) · better on 3 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
- HumanRig: Learning Automatic Rigging for Humanoid Character in a Large Scale Dataset (CVPR 2025 · similarity 0.92)
- Puppeteer: Rig and Animate Your 3D Models (NeurIPS 2025 · similarity 0.89)
- Rigel3D: Rig-aware Latents for Animation-Ready 3D Asset Generation (NeurIPS 2026 · similarity 0.89)
- DIPO: Dual-State Images Controlled Articulated Object Generation Powered by Diverse Data (NeurIPS 2025 · similarity 0.88)
- SKDream: Controllable Multi-view and 3D Generation with Arbitrary Skeletons (CVPR 2025 · similarity 0.88)
- TapMo: Shape-aware Motion Generation of Skeleton-free Characters (ICLR 2024 · similarity 0.88)
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.
