Research map / 3D vision / Face and shape
Learning Category-Specific 3D Shape Models From Weakly Labeled 2D Images
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 |
|---|---|---|---|
| add a cluster-level learning curriculum to joint shape reconstruction and object segmentation (ablation) | category-specific 3D shape learning · PASCAL VOC 2012 categories, mean | Mesh error: 4.46 -> 4.09 | Helped |
| add a cluster-level learning curriculum to joint shape reconstruction and object segmentation (ablation) | category-specific 3D shape learning · PASCAL VOC 2012 categories, mean | Depth error: 18.58 -> 18.18 | Helped |
| add a cluster-level learning curriculum (ablation) | common object segmentation · PASCAL VOC 2012 categories, mean | IOU: 0.714 -> 0.743 | Helped |
| jointly learn shape reconstruction and segmentation instead of reconstructing shapes from initial co-segmentation masks alone (ablation) | category-specific 3D shape learning · PASCAL VOC 2012 categories, mean | Mesh error: 4.64 -> 4.46 | Helped |
| jointly learn shape reconstruction and segmentation instead of reconstructing shapes from initial co-segmentation masks alone (ablation) | category-specific 3D shape learning · PASCAL VOC 2012 categories, mean | Depth error: 19.58 -> 18.58 | Helped |
| jointly learn shape reconstruction and segmentation instead of reconstructing shapes from initial co-segmentation masks alone (ablation) | common object segmentation · PASCAL VOC 2012 categories, mean | IOU: 0.710 -> 0.714 | Helped |
| use the full weakly supervised framework rather than the strongest reported segmentation baseline | common object segmentation · PASCAL VOC 2012 categories, mean | IOU: 0.689 -> 0.743 | Helped |
Closest papers by meaning
- Unsupervised Learning of 3D Object Categories From Videos in the Wild (CVPR 2021 · similarity 0.89)
- Learning 3D Object Shape and Layout Without 3D Supervision (CVPR 2022 · similarity 0.88)
- Canonical 3D Deformer Maps: Unifying parametric and non-parametric methods for dense weakly-supervised category reconstruction (NeurIPS 2020 · similarity 0.88)
- Common3D: Self-Supervised Learning of 3D Morphable Models for Common Objects in Neural Feature Space (CVPR 2025 · similarity 0.88)
- Unsupervised 3D Structure Inference from Category-Specific Image Collections (CVPR 2024 · similarity 0.88)
- 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.