Research map / 3D vision / Face and shape
Self-Supervised Neural Articulated Shape and Appearance Models
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use category-level shape, appearance, and articulation priors rather than fitting IDR from 6 views | Ours-ArtDef vs IDR 6 views · synthetic articulated objects | Chamfer-L1 and PSNR | Mixed |
| Add a deformation field to handle articulation (ablation) | Ours-ArtDef · articulated objects with topology changes | geometry quality | Helped |
| Add shared articulation codes (ablation) | Ours-ArtDef · synthetic articulated objects | Chamfer-L1 | Mixed |
| Add a deformation field (ablation) | Ours-ArtDef · synthetic articulated objects | Chamfer-L1 | Mixed |
| Apply test-time adaptation to network weights and codes (ablation) | Ours-ArtDef · synthetic articulated objects | Chamfer-L1 | Mixed |
| Apply test-time adaptation to network weights and codes (ablation) | Ours-ArtDef · synthetic articulated objects | PSNR | Mixed |
| Use a deformation field rather than no deformation field (ablation) | Ours-Def and Ours-ArtDef · articulations involving topology changes | geometry quality | Helped |
| Use RGB-only category priors instead of fitting a single-object model to 6 views | Ours-ArtDef vs IDR 6 views · unseen synthetic objects | PSNR | Helped |
| Use RGB-only supervision instead of 3D-supervised A-SDF | Ours-ArtDef vs A-SDF · articulated object reconstruction | Chamfer-L1 | Mixed |
| Use learned articulation codes without ground-truth joint labels | Ours-ArtDef · sliding-joint objects | geometry quality | Helped |
Closest papers by meaning
- Learning Implicit Representation for Reconstructing Articulated Objects (ICLR 2024 · similarity 0.89)
- Common3D: Self-Supervised Learning of 3D Morphable Models for Common Objects in Neural Feature Space (CVPR 2025 · similarity 0.88)
- ArticulatedGS: Self-supervised Digital Twin Modeling of Articulated Objects using 3D Gaussian Splatting (CVPR 2025 · similarity 0.87)
- SINGAPO: Single Image Controlled Generation of Articulated Parts in Objects (ICLR 2025 · similarity 0.87)
- Articulate your NeRF: Unsupervised articulated object modeling via conditional view synthesis (NeurIPS 2024 · similarity 0.87)
- Learning Partonomic 3D Reconstruction from Image Collections (CVPR 2025 · 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.