Research map / 3D vision / Face and shape
Discovering Relationships Between Object Categories via Universal Canonical Maps
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 ZoomOut initialization rather than random initialization | Universal canonical map training · DensePose-LVIS | AP: 25.4→35.1 | Helped |
| Use ZoomOut initialization rather than random initialization | Universal canonical map training · DensePose-LVIS | GErr: 23.7 → 28.0 | Hurt |
| Train on the expanded DensePose-LVIS v1.0 data | Universal canonical map · DensePose-LVIS v1.0 | AP: 35.1→37.4 | Helped |
| Add m2m cycle consistency (ablation) | Universal canonical map · Animals only | AP: 37.5→38.2 | Helped |
| Add m2m cycle consistency (ablation) | Universal canonical map · Animals only | GErr: 14.05 → 11.96 | Helped |
| Add i2m image-to-mesh cycle consistency (ablation) | Universal canonical map · Animals only | AP: 37.5→38.1 | Helped |
| Add i2m image-to-mesh cycle consistency (ablation) | Universal canonical map · Animals only | GErr: 14.05 → 12.67 | Helped |
| Apply i2m across categories (ablation) | Universal canonical map · Animals only | AP: 37.5→38.3 | Helped |
| Add m2m and i2m cycle consistency (ablation) | Universal canonical map · Animals only | GErr: 14.05 → 11.37 | Helped |
| Add m2m and apply i2m across categories (ablation) | Universal canonical map · Animals only | AP: 37.5→38.5 | Helped |
| Add m2m and apply i2m across categories (ablation) | Universal canonical map · Animals only | GErr: 14.05 → 10.90 | Helped |
| Add m2m rather than using the baseline (ablation) | Universal canonical map · PASCAL VOC keypoint transfer within training animal categories | PCK-Transfer: 47.1→46.8 | Hurt |
Closest papers by meaning
- Unsupervised Learning of Category-Level 3D Pose from Object-Centric Videos (CVPR 2024 · similarity 0.88)
- Universal Features Guided Zero-Shot Category-Level Object Pose Estimation (AAAI 2025 · similarity 0.88)
- Jamais Vu: Exposing the Generalization Gap in Supervised Semantic Correspondence (NeurIPS 2025 · similarity 0.87)
- DenseMatcher: Learning 3D Semantic Correspondence for Category-Level Manipulation from a Single Demo (ICLR 2025 · similarity 0.86)
- SchemaPose: RGB-Based Category-Level Pose Estimation with Parametric Category Schema (NeurIPS 2026 · 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.