Research map / 3D vision / Face and shape
Shelf-Supervised Mesh Prediction in the Wild
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 the proposed volumetric reconstruction method instead of the strongest baseline | Shelf-Supervised Mesh Prediction · 3D Warehouse airplane | 3D IoU: 0.29 -> 0.33 | Helped |
| Use the proposed volumetric reconstruction method instead of the strongest baseline | Shelf-Supervised Mesh Prediction · 3D Warehouse car | 3D IoU: 0.48 -> 0.55 | Helped |
| Use the proposed volumetric reconstruction method instead of the strongest baseline | Shelf-Supervised Mesh Prediction · 3D Warehouse chair | 3D IoU: 0.28 -> 0.31 | Helped |
| Add mesh refinement after volume-to-mesh initialization | Shelf-Supervised Mesh Prediction · 3D Warehouse airplane | F-score: 0.46 -> 0.49 | Helped |
| Add mesh refinement after volume-to-mesh initialization | Shelf-Supervised Mesh Prediction · 3D Warehouse car | F-score: 0.43 -> 0.42 | Hurt |
| Add mesh refinement after volume-to-mesh initialization | Shelf-Supervised Mesh Prediction · 3D Warehouse chair | F-score: 0.29 -> 0.31 | Helped |
| Add the adversarial loss (ablation) | Shelf-Supervised Mesh Prediction · 3D Warehouse airplane | 3D IoU: 0.25 -> 0.33 | Helped |
| Add the adversarial loss (ablation) | Shelf-Supervised Mesh Prediction · 3D Warehouse car | 3D IoU: 0.44 -> 0.55 | Helped |
| Add the adversarial loss (ablation) | Shelf-Supervised Mesh Prediction · 3D Warehouse chair | 3D IoU: 0.22 -> 0.31 | Helped |
| Add the content consistency loss (ablation) | Shelf-Supervised Mesh Prediction · 3D Warehouse airplane | 3D IoU: 0.24 -> 0.33 | Helped |
| Add the content consistency loss (ablation) | Shelf-Supervised Mesh Prediction · 3D Warehouse car | 3D IoU: 0.54 -> 0.55 | Helped |
| Add the content consistency loss (ablation) | Shelf-Supervised Mesh Prediction · 3D Warehouse chair | 3D IoU: 0.23 -> 0.31 | Helped |
Closest papers by meaning
- Unsupervised Learning of Shape and Pose with Differentiable Point Clouds (NeurIPS 2018 · similarity 0.88)
- Unsupervised Learning of Category-Level 3D Pose from Object-Centric Videos (CVPR 2024 · similarity 0.86)
- SAOR: Single-View Articulated Object Reconstruction (CVPR 2024 · similarity 0.85)
- ShapeMatcher: Self-Supervised Joint Shape Canonicalization Segmentation Retrieval and Deformation (CVPR 2024 · similarity 0.85)
- Common3D: Self-Supervised Learning of 3D Morphable Models for Common Objects in Neural Feature Space (CVPR 2025 · similarity 0.85)
- Unsupervised 3D Structure Inference from Category-Specific Image Collections (CVPR 2024 · 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.