Research map / 3D vision / Face and shape
3D Shape Attributes
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 |
|---|---|---|---|
| infer shape attributes directly from the image rather than estimating depth then deriving attributes | 3D shape attribute prediction · Sculpture Images Test | mean AUC: 62.5 -> 72.3 | Helped |
| replace VGG-M with VGG-16 (ablation) | Proposed attribute predictor · Sculpture Images Test | mean AUC: 72.3 -> 74.4 | Helped |
| train only for attributes, removing the shape embedding loss (ablation) | Sculpture shape representation · Mental rotation — All | AUC: 92.3 -> 89.8 | Hurt |
| train only for attributes, removing the shape embedding loss (ablation) | Sculpture shape representation · Mental rotation — Hard | AUC: 86.9 -> 82.5 | Hurt |
| use the attribute-only network instead of the pretrained representation (ablation) | Sculpture shape representation · Mental rotation — All | AUC: 88.9 -> 89.8 | Helped |
| use the attribute-only network instead of the pretrained representation (ablation) | Sculpture shape representation · Mental rotation — Hard | AUC: 80.0 -> 82.5 | Helped |
| train a full network with both attribute and embedding objectives instead of using pretrained FC7 | Sculpture shape representation · Mental rotation — All | AUC: 88.9 -> 92.3 | Helped |
| train a full network with both attribute and embedding objectives instead of using pretrained FC7 | Sculpture shape representation · Mental rotation — Hard | AUC: 80.0 -> 86.9 | Helped |
Closest papers by meaning
- Factoring Shape, Pose, and Layout From the 2D Image of a 3D Scene (CVPR 2018 · similarity 0.89)
- Learning Unsupervised Hierarchical Part Decomposition of 3D Objects From a Single RGB Image (CVPR 2020 · similarity 0.88)
- SurfNet: Generating 3D Shape Surfaces Using Deep Residual Networks (CVPR 2017 · similarity 0.88)
- Do 2D GANs Know 3D Shape? Unsupervised 3D Shape Reconstruction from 2D Image GANs (ICLR 2021 · similarity 0.88)
- Common3D: Self-Supervised Learning of 3D Morphable Models for Common Objects in Neural Feature Space (CVPR 2025 · similarity 0.87)
- Learning Partonomic 3D Reconstruction from Image Collections (CVPR 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.