Research map / 3D vision / Face and shape
Instant Volumetric Head Avatars
Read the paperCheck 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 INSTA instead of NeRFace | monocular-video head avatar reconstruction · 19-video test set | LPIPS: 0.07 -> 0.05 | Helped |
| Use INSTA instead of NeRFace | monocular-video head avatar reconstruction · 19-video test set | L2: 0.0018 -> 0.0018 | No clear effect |
| Use INSTA instead of NeRFace | monocular-video head avatar reconstruction · 19-video test set | PSNR: 29.28 -> 28.97 | Hurt |
| Use INSTA instead of NeRFace | monocular-video head avatar reconstruction · 19-video test set | rendering time per frame (seconds): 9.68 -> 0.05 | Helped |
| Use INSTA instead of IMAvatar | monocular-video head avatar reconstruction · 19-video test set | LPIPS: 0.06 -> 0.05 | Helped |
| Use INSTA instead of NHA | monocular-video head avatar reconstruction · 19-video test set | LPIPS: 0.04 -> 0.05 | Hurt |
| Replace localized expression conditioning with global conditioning (ablation) | INSTA · short training sequences | rendering quality | Hurt |
| Remove the deformation field and add per-frame learnable codes (ablation) | INSTA · short training sequences | rendering quality | Hurt |
| Add the FLAME geometric depth prior (ablation) | INSTA · extreme novel-view extrapolation | rendering stability and quality | Helped |
| Add localized FLAME expression conditioning in the mouth (ablation) | INSTA · mouth interior synthesis | synthesis quality | Helped |
| Increase the color-loss weight on the mouth region (ablation) | INSTA · mouth reconstruction | visual quality | Helped |
Closest papers by meaning
- FlashAvatar: High-fidelity Head Avatar with Efficient Gaussian Embedding (CVPR 2024 · similarity 0.88)
- High-Fidelity 3D Head Avatars Reconstruction through Spatially-Varying Expression Conditioned Neural Radiance Field (AAAI 2024 · similarity 0.88)
- GPAvatar: High-fidelity Head Avatars by Learning Efficient Gaussian Projections (CVPR 2025 · similarity 0.88)
- RGBAvatar: Reduced Gaussian Blendshapes for Online Modeling of Head Avatars (CVPR 2025 · similarity 0.88)
- HERA: Hybrid Explicit Representation for Ultra-Realistic Head Avatars (CVPR 2025 · similarity 0.88)
- Efficient 3D Implicit Head Avatar with Mesh-anchored Hash Table Blendshapes (CVPR 2024 · 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.