Research map / 3D vision / Face and shape
Learning To Aggregate and Personalize 3D Face From In-the-Wild Photo Collection
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 |
|---|---|---|---|
| remove curriculum learning (ablation) | LAP · BFM | SIDE (× 10⁻²): 0.721 -> 2.011 | Hurt |
| remove curriculum learning (ablation) | LAP · BFM | MAD (deg.): 15.53 -> 23.07 | Hurt |
| remove relaxed consistency loss (ablation) | LAP · BFM | SIDE (× 10⁻²): 0.721 -> 0.738 | Hurt |
| replace adaptive aggregation with average fusion (ablation) | LAP · BFM | SIDE (× 10⁻²): 0.721 -> 0.764 | Hurt |
| remove filtered connection (ablation) | LAP · BFM | SIDE (× 10⁻²): 0.721 -> 0.725 | No clear effect |
| use only the highest-level feature vector for attribute injection (ablation) | LAP · BFM | SIDE (× 10⁻²): 0.721 -> 0.750 | Hurt |
| increase output size to 256×256 (ablation) | LAP · BFM | SIDE (× 10⁻²): 0.721 -> 0.703 | Helped |
| use more images in the input photo collection | LAP · CelebAMask-HQ | SSIM | Helped |
Closest papers by meaning
- Learning Neural Proto-Face Field for Disentangled 3D Face Modeling in the Wild (CVPR 2023 · similarity 0.87)
- Learning Person-Specific Animatable Face Models from In-the-Wild Images via a Shared Base Model (CVPR 2025 · similarity 0.87)
- Adaptive 3D Face Reconstruction From Unconstrained Photo Collections (CVPR 2016 · similarity 0.87)
- Learning Complete 3D Morphable Face Models From Images and Videos (CVPR 2021 · similarity 0.86)
- Self-Supervised Multi-Level Face Model Learning for Monocular Reconstruction at Over 250 Hz (CVPR 2018 · similarity 0.86)
- Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstruction (ICLR 2026 · 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.