Research map / 3D vision / Face and shape
Self-Supervised 3D Mesh Reconstruction From Single 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 interpolated consistency to 2D supervision (ablation) | SMR · ShapeNet | 3D IoU (%): 42.8 -> 46.0 | Helped |
| Add landmark consistency to 2D supervision plus interpolated consistency (ablation) | SMR · ShapeNet | 3D IoU (%): 46.0 -> 46.5 | Helped |
| Use cycle consistency instead of interpolated consistency (ablation) | 2D supervised reconstruction · ShapeNet | 3D IoU (%): 42.8 -> 43.5 | Helped |
| Add interpolated consistency (ablation) | Unsup3D · BFM | SIDE (×10−2): 0.793 -> 0.762 | Helped |
| Add interpolated consistency (ablation) | Unsup3D · BFM | MAD (deg.): 16.51 -> 14.94 | Helped |
| Add landmark consistency (ablation) | Unsup3D · BFM | SIDE (×10−2): 0.793 -> 0.763 | Helped |
| Add landmark consistency (ablation) | Unsup3D · BFM | MAD (deg.): 16.51 -> 14.64 | Helped |
| Add interpolated and landmark consistency (ablation) | Unsup3D · BFM | SIDE (×10−2): 0.793 -> 0.758 | Helped |
| Add interpolated and landmark consistency (ablation) | Unsup3D · BFM | MAD (deg.): 16.51 -> 14.55 | Helped |
| Add SMR's self-supervised methods to silhouette-supervised reconstruction | single-view mesh reconstruction · CUB-200-2011 | Mask IoU (%): 73.4 -> 80.6 | Helped |
| Add SMR's self-supervised methods to silhouette-supervised reconstruction | single-view mesh reconstruction · CUB-200-2011 | PCK (%): 58.2 -> 62.2 | Helped |
| Add SMR's self-supervised methods to silhouette-supervised reconstruction | single-view mesh reconstruction · CUB-200-2011 novel views | FID: 83.6 -> 79.2 | Helped |
Closest papers by meaning
- SAOR: Single-View Articulated Object Reconstruction (CVPR 2024 · similarity 0.88)
- Self-Supervised 3D Human Mesh Recovery from a Single Image with Uncertainty-Aware Learning (AAAI 2024 · similarity 0.86)
- Learning Partonomic 3D Reconstruction from Image Collections (CVPR 2025 · similarity 0.86)
- Self-Supervised Dual Contouring (CVPR 2024 · similarity 0.85)
- MeshFormer : High-Quality Mesh Generation with 3D-Guided Reconstruction Model (NeurIPS 2024 · similarity 0.85)
- Common3D: Self-Supervised Learning of 3D Morphable Models for Common Objects in Neural Feature Space (CVPR 2025 · similarity 0.85)
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.