Research map / 3D vision / Depth and stereo
Instant Multi-View Head Capture Through Learnable Registration
Timo Bolkart, Tianye Li, Michael J. Black
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 |
|---|---|---|---|
| Train from raw scans using scan-to-mesh surface distance loss (ablation) | TEMPEH · FaMoS test set, complete head | median reconstruction error (mm): 0.78 -> 0.26 | Improved |
| Add head localization with a spatial transformer (ablation) | TEMPEH coarse stage · FaMoS test set, complete head | median reconstruction error (mm): 1.16 -> 0.71 | Improved |
| Add head localization with a spatial transformer (ablation) | TEMPEH · FaMoS test set, complete head | median reconstruction error (mm): 0.28 -> 0.26 | Improved |
| Use surface- and visibility-aware feature fusion (ablation) | TEMPEH refinement · FaMoS test set, complete head | median reconstruction error (mm): 0.35 -> 0.26 | Improved |
| Use grayscale stereo images rather than color images (ablation) | TEMPEH · FaMoS test set, complete head | median reconstruction error (mm): 0.44 -> 0.26 | Improved |
| Use a non-hierarchical architecture rather than a hierarchical mesh architecture (ablation) | TEMPEH · FaMoS test set, complete head | median reconstruction error (mm): 0.27 -> 0.26 | Improved |
| Use TEMPEH instead of ToFu | 3D head reconstruction · FaMoS test set, complete head | median reconstruction error (mm): 0.72 -> 0.26 | Improved |
| Use TEMPEH instead of ToFu+ | 3D head reconstruction · FaMoS test set, complete head | median reconstruction error (mm): 0.82 -> 0.26 | Improved |
Closest papers by meaning
- Registration-Free Learnable Multi-View Capture of Faces in Dense Semantic Correspondence (CVPR 2026 · similarity 0.90)
- Multi-view Consistent 3D Gaussian Head Avatars 'without' Multi-view Generation (CVPR 2026 · similarity 0.88)
- Implicit Shape and Appearance Priors for Few-Shot Full Head Reconstruction (TPAMI 2025 · similarity 0.88)
- H3D-Net: Few-Shot High-Fidelity 3D Head Reconstruction (ICCV 2021 · similarity 0.87)
- Large-Scale High-Quality 3D Gaussian Head Reconstruction from Multi-View Captures (ECCV 2026 · similarity 0.87)
- Synthetic Prior for Few-Shot Drivable Head Avatar Inversion (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.
