Research map / 3D vision / Face and shape
Implicit Shape and Appearance Priors for Few-Shot Full Head Reconstruction
Pol Caselles, Eduard Ramon, Jaime García, Gil Triginer, Francesc Moreno-Noguer
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 |
|---|---|---|---|
| add progressive masking and fine-tune geometry decoder (ablation) | H3D-Net · H3DS ablation (23 scenes, 1 view) | face surface error (mm): 1.97 -> 2.17 | Hurt |
| split geometry into deformation field plus reference SDF (ablation) | H3D-Net + progressive masking · H3DS ablation (23 scenes, 1 view) | face surface error (mm): 2.17 -> 1.86 | Improved |
| add joint shape and appearance prior (SA-SM) (ablation) | H3D-Net + deformation field + reference SDF · H3DS ablation (23 scenes, 1 view) | face surface error (mm): 1.86 -> 1.46 | Improved |
| add joint shape and appearance prior (SA-SM) (ablation) | H3D-Net + deformation field + reference SDF · H3DS ablation (23 scenes, 1 view) | head surface error (mm): 13.40 -> 14.16 | Hurt |
| add progressive masking (ablation) | H3D-Net · H3DS ablation (23 scenes, 4 views) | face surface error (mm): 1.49 -> 1.54 | Hurt |
| split geometry into deformation field plus reference SDF (ablation) | H3D-Net + progressive masking · H3DS ablation (23 scenes, 4 views) | head surface error (mm): 10.61 -> 9.00 | Improved |
| add joint shape and appearance prior (SA-SM) (ablation) | H3D-Net + deformation field + reference SDF · H3DS ablation (23 scenes, 4 views) | face surface error (mm): 1.38 -> 1.29 | Improved |
| add selective sampling (ablation) | SIRA++ without cache · H3DS 2.0 (3 views, test time) | test time: 379s -> 275s | Improved |
| add dynamic SDF caching (ablation) | SIRA++ without selective sampling · H3DS 2.0 (3 views, test time) | test time: 379s -> 232s | Improved |
| add both selective sampling and caching (ablation) | SIRA++ · H3DS 2.0 (3 views, test time) | test time: 379s -> 191s | Improved |
| add shape and appearance prior versus H3D-Net | H3D-Net · H3DS 2.0 (1 view vs 3 views) mean error | face surface error (mm): 1.44 -> 1.18 | Improved |
| add camera pose noise sigma 0.04 (ablation) | H3D-Net vs SIRA++ · H3DS 3 views, camera noise | head surface error (mm): 13.36 vs 11.84 | Mixed |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- NeuS2 — NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstruction (ICCV 2023) · better on 1 of 1 shared result
- JIFF — JIFF: Jointly-Aligned Implicit Face Function for High Quality Single View Clothed Human Reconstruction (CVPR 2022) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- H3D-Net: Few-Shot High-Fidelity 3D Head Reconstruction (ICCV 2021 · similarity 0.96)
- Deformable Model-Driven Neural Rendering for High-Fidelity 3D Reconstruction of Human Heads Under Low-View Settings (ICCV 2023 · similarity 0.89)
- Skullptor: High Fidelity 3D Head Reconstruction in Seconds with Multi-View Normal Prediction (CVPR 2026 · similarity 0.89)
- Front2Back: Single View 3D Shape Reconstruction via Front to Back Prediction (CVPR 2020 · similarity 0.88)
- Deep Optimized Priors for 3D Shape Modeling and Reconstruction (CVPR 2021 · similarity 0.88)
- Fostering Generalization in Single-View 3D Reconstruction by Learning a Hierarchy of Local and Global Shape Priors (CVPR 2021 · similarity 0.88)
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.
