Research map / 3D vision / Face and shape
Learning Category-Specific Mesh Reconstruction from Image Collections
Angjoo Kanazawa, Shubham Tulsiani, Alexei A. Efros, Jitendra Malik
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 predicted per-instance deformation on top of the learned mean shape (ablation) | CMR mesh predictor · CUB-200-2011 test (keypoint reprojection, threshold 0.1) | PCK: 0.80 -> 0.81 | Improved |
| add predicted per-instance deformation on top of the learned mean shape (ablation) | CMR mesh predictor · CUB-200-2011 test (mask reprojection IoU) | mask IoU | Improved |
| use predicted camera instead of structure-from-motion camera from ground-truth keypoints (ablation) | CMR mesh predictor · CUB-200-2011 test (mask reprojection IoU) | mask IoU | No clear effect |
Closest papers by meaning
- Shape and Viewpoint without Keypoints (ECCV 2020 · similarity 0.92)
- Self-supervised Single-view 3D Reconstruction via Semantic Consistency (ECCV 2020 · similarity 0.92)
- Learning Category-Specific 3D Shape Models From Weakly Labeled 2D Images (CVPR 2017 · similarity 0.91)
- Learning Category-Specific Deformable 3D Models for Object Reconstruction (TPAMI 2016 · similarity 0.91)
- Common3D: Self-Supervised Learning of 3D Morphable Models for Common Objects in Neural Feature Space (CVPR 2025 · similarity 0.89)
- Learning Partonomic 3D Reconstruction from Image Collections (CVPR 2025 · similarity 0.88)
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.
