Research map / 3D vision / Face and shape
Object Wake-Up: 3D Object Rigging from a Single Image
Ji Yang, Xinxin Zuo, Sen Wang, Zhenbo Yu, Xingyu Li, Bingbing Ni, Minglun Gong, Li Cheng
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 |
|---|---|---|---|
| add joint-aware instance segmentation (ablation) | skeleton prediction baseline · SSkel | CD-J2J: 0.065 -> 0.055 | Improved |
| add joint-aware instance segmentation (ablation) | skeleton prediction baseline · RigNetv1 | CD-J2J: 0.037 -> 0.033 | Improved |
| add symmetry loss (ablation) | skeleton prediction baseline · SSkel | CD-J2J: 0.065 -> 0.058 | Improved |
| add symmetry loss (ablation) | skeleton prediction baseline · RigNetv1 | CD-J2J: 0.037 -> 0.034 | Improved |
| add 3D adaptive channel activation (ablation) | skeleton prediction baseline · SSkel | CD-J2J: 0.065 -> 0.056 | Improved |
| add 3D adaptive channel activation (ablation) | skeleton prediction baseline · RigNetv1 | CD-J2J: 0.037 -> 0.033 | Improved |
| combine all three components (ablation) | skeleton prediction baseline · SSkel | CD-J2J: 0.065 -> 0.047 | Improved |
| combine all three components (ablation) | skeleton prediction baseline · RigNetv1 | CD-J2J: 0.037 -> 0.029 | Improved |
| use reconstructed 3D models instead of ground-truth as skeleton input | Ours · SSkel | CD-J2J: 0.047 -> 0.051 | Hurt |
| use volumetric point-based skeleton prediction instead of RigNet | skeleton prediction · RigNetv1 | CD-J2J: 0.039 -> 0.029 | Improved |
| use our reconstruction instead of D2IM-Net | image-to-3D · Pix3D | Chamfer distance avg (x0.001): 9.057 -> 7.282 | Improved |
| use our reconstruction instead of D2IM-Net | image-to-3D · ShapeRR (re-rendered ShapeNet) | Chamfer distance avg (x0.001): 2.0346 -> 1.9301 | 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
- REACTO: Reconstructing Articulated Objects from a Single Video (CVPR 2024 · similarity 0.88)
- SINGAPO: Single Image Controlled Generation of Articulated Parts in Objects (ICLR 2025 · similarity 0.88)
- SKDream: Controllable Multi-view and 3D Generation with Arbitrary Skeletons (CVPR 2025 · similarity 0.86)
- Learning Implicit Representation for Reconstructing Articulated Objects (ICLR 2024 · similarity 0.86)
- RigGS: Rigging of 3D Gaussians for Modeling Articulated Objects in Videos (CVPR 2025 · similarity 0.86)
- Puppeteer: Rig and Animate Your 3D Models (NeurIPS 2025 · similarity 0.86)
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.
