Research map / 3D vision / Face and shape
Canonical 3D Deformer Maps: Unifying parametric and non-parametric methods for dense weakly-supervised category reconstruction
Read the paperCheck 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 |
|---|---|---|---|
| add reprojection loss (ablation) | C3DM · Freiburg Cars | d_pcl: 0.247 -> 0.123 | Helped |
| add basis loss (ablation) | C3DM · Freiburg Cars | d_pcl: 0.462 -> 0.123 | Helped |
| add min-k perceptual (appearance) loss (ablation) | C3DM · Freiburg Cars | d_pcl: 0.141 -> 0.123 | Helped |
| add min-k perceptual (appearance) loss (ablation) | C3DM · Florence Face | d_pcl: 5.647 -> 5.574 | Helped |
| add embedding-alignment loss (ablation) | C3DM · Freiburg Cars | d_pcl: 0.186 -> 0.123 | Helped |
| add embedding-alignment loss (ablation) | C3DM · Florence Face | d_pcl: 5.592 -> 5.574 | Helped |
| add reprojection loss (ablation) | C3DM · Florence Face | d_pcl: 6.582 -> 5.574 | Helped |
| use dense canonical map instead of fixed-topology mesh interpolation (ablation) | C3DM · Florence Face | d_pcl: 13.721 -> 5.574 | Helped |
| C3DM point-cloud representation instead of CMR mesh | category 3D reconstruction · Florence Face | d_pcl: 13.09 -> 5.57 | Helped |
| C3DM instead of CMR | category 3D reconstruction · Pascal3D+ Car | d_pcl: 0.028 -> 0.028 | No clear effect |
Closest papers by meaning
- Unsupervised Learning of Probably Symmetric Deformable 3D Objects From Images in the Wild (CVPR 2020 · similarity 0.90)
- Discovering Relationships Between Object Categories via Universal Canonical Maps (CVPR 2021 · similarity 0.90)
- Continuous Surface Embeddings (NeurIPS 2020 · similarity 0.90)
- ShapeMatcher: Self-Supervised Joint Shape Canonicalization Segmentation Retrieval and Deformation (CVPR 2024 · similarity 0.87)
- Implicit Modeling of Non-rigid Objects with Cross-Category Signals (AAAI 2024 · similarity 0.86)
- One-shot 3D Object Canonicalization based on Geometric and Semantic Consistency (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.