Research map / 3D vision / Face and shape
SPAMs: Structured Implicit Parametric 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 |
|---|---|---|---|
| replace whole-object fitting with structured part-based shape and pose spaces | SPAMs versus NPMs* · RenderPeople test set | IoU: 0.755 -> 0.785 | Helped |
| replace whole-object fitting with structured part-based shape and pose spaces | SPAMs versus NPMs* · RenderPeople test set | C-ℓ2: 0.00163 -> 0.00032 | Helped |
| replace whole-object fitting with structured part-based shape and pose spaces | SPAMs versus NPMs* · RenderPeople test set | NC: 0.856 -> 0.883 | Helped |
| replace whole-object fitting with structured part-based shape and pose spaces | SPAMs versus NPMs* · RenderPeople test set | EPE: 0.053 -> 0.034 | Helped |
| add pose encoder initialization (ablation) | SPAMs · RenderPeople test set | EPE: 0.052 -> 0.034 | Helped |
| add part grid mask (ablation) | SPAMs · RenderPeople test set | EPE: 0.037 -> 0.034 | Helped |
| add both pose encoder initialization and part grid mask (ablation) | SPAMs · RenderPeople test set | IoU: 0.671 -> 0.785 | Helped |
| use ground-truth part segmentation instead of predicted part labels (ablation) | SPAMs · RenderPeople test set | EPE: 0.034 -> 0.026 | Helped |
| remove pose encoder initialization (ablation) | NPMs* · RenderPeople test set | EPE: 0.053 -> 0.182 | Hurt |
Closest papers by meaning
- Implicit Modeling of Non-rigid Objects with Cross-Category Signals (AAAI 2024 · similarity 0.89)
- Neural Pose Representation Learning for Generating and Transferring Non-Rigid Object Poses (NeurIPS 2024 · similarity 0.88)
- Learning Implicit Representation for Reconstructing Articulated Objects (ICLR 2024 · similarity 0.87)
- Learning Partonomic 3D Reconstruction from Image Collections (CVPR 2025 · similarity 0.86)
- REACTO: Reconstructing Articulated Objects from a Single Video (CVPR 2024 · similarity 0.86)
- Motion2VecSets: 4D Latent Vector Set Diffusion for Non-rigid Shape Reconstruction and Tracking (CVPR 2024 · 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.