Research map / 3D vision / Face and shape
Head Reconstruction from Internet Photos
Shu Liang, Linda G. Shapiro, Ira Kemelmacher-Shlizerman
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 |
|---|---|---|---|
| replace FaceGen morphable model with boundary-value growing | FaceGen · Internet photos, Bush | reprojection error: 20.6 -> 18.3 | Improved |
| replace shape-from-silhouette with boundary-value growing | Shape-from-Silhouette · Internet photos, Putin | reprojection error: 17.2 -> 15.1 | Improved |
| replace shape-from-silhouette with boundary-value growing | Shape-from-Silhouette · Internet photos, Obama | reprojection error: 20.7 -> 19.7 | Improved |
| use half the photos per view cluster (ablation) | Boundary-value growing · Bush, 600 photos | reprojection error: 18.29 -> 18.70 | No clear effect |
| use one eighth of the photos per view cluster (ablation) | Boundary-value growing · Bush, 600 photos | reprojection error: 18.29 -> 18.80 | Hurt |
| use one sixteenth of the photos per view cluster (ablation) | Boundary-value growing · Bush, 600 photos | reconstruction success | Hurt |
| add ambiguity recovery from neighbor view and Dirichlet depth constraint (ablation) | Independent per-view photometric stereo · 90-degree view reconstruction | qualitative shape | Improved |
| add more photos to space carving | Space Carving · Internet photos | reconstruction quality | No clear effect |
Closest papers by meaning
- Adaptive 3D Face Reconstruction From Unconstrained Photo Collections (CVPR 2016 · similarity 0.87)
- GPHM: Gaussian Parametric Head Model for Monocular Head Avatar Reconstruction (TPAMI 2025 · similarity 0.85)
- Sparse Photometric 3D Face Reconstruction Guided by Morphable Models (CVPR 2018 · similarity 0.85)
- RGBAvatar: Reduced Gaussian Blendshapes for Online Modeling of Head Avatars (CVPR 2025 · similarity 0.85)
- PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing (CVPR 2025 · similarity 0.85)
- HRAvatar: High-Quality and Relightable Gaussian Head Avatar (CVPR 2025 · similarity 0.84)
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.
