Research map / 3D vision / Face and shape
SVG-Head: Hybrid Surface-Volumetric Gaussians for High-Fidelity Head Reconstruction and Real-Time Editing
Heyi Sun, Cong Wang, Tian-Xing Xu, Jingwei Huang, Di Kang, Chunchao Guo, Song-Hai Zhang
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 |
|---|---|---|---|
| constrain surf-GS on the mesh with fixed rotations (ablation) | SVG-Head · NeRSemble Subject 306 | PSNR: 30.0/29.6 -> 30.9 | Improved |
| use hierarchical two-stage optimization instead of joint from scratch (ablation) | SVG-Head · NeRSemble Subject 306 | PSNR: 28.0 -> 30.9 | Improved |
| optimize only opacity and dynamic texture of surf-GS instead of freezing all (ablation) | SVG-Head · NeRSemble Subject 306 | PSNR: 30.1 -> 30.9 | Improved |
| optimize only opacity and dynamic texture of surf-GS instead of all (ablation) | SVG-Head · NeRSemble Subject 306 | PSNR: 28.4 -> 30.9 | Improved |
| add diffuse photometric loss (ablation) | SVG-Head · NeRSemble Subject 306 | PSNR: 31.1 -> 30.9 | No clear effect |
| add alpha loss in joint stage (ablation) | SVG-Head · NeRSemble Subject 306 | PSNR: 30.2 -> 30.9 | Improved |
| use surface Gaussians instead of mesh with RGB colors (ablation) | VHAP · NeRSemble Subject 306 | PSNR: 29.8 -> 31.3 | Improved |
| add SH coefficients to surface Gaussians (ablation) | Surf-GS · NeRSemble Subject 306 | PSNR: 31.3 -> 33.3 | Improved |
| add SH coefficients to mesh optimization (ablation) | VHAP · NeRSemble Subject 306 | PSNR: 29.8 -> 17.5 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 3 on most shared results.
- Gaussian Head Avatar — Gaussian Head Avatar: Ultra High-fidelity Head Avatar via Dynamic Gaussians (CVPR 2024) · better on 5 of 5 shared results
- GaussianAvatars — GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians (CVPR 2024) · better on 0 of 5 shared results
- PointAvatar — PointAvatar: Deformable Point-Based Head Avatars From Videos (CVPR 2023) · better on 4 of 4 shared results
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
- MeGA: Hybrid Mesh-Gaussian Head Avatar for High-Fidelity Rendering and Head Editing (CVPR 2025 · similarity 0.92)
- Gaussian Head Avatar: Ultra High-fidelity Head Avatar via Dynamic Gaussians (CVPR 2024 · similarity 0.90)
- GPAvatar: High-fidelity Head Avatars by Learning Efficient Gaussian Projections (CVPR 2025 · similarity 0.90)
- 3D Gaussian Head Avatars with Expressive Dynamic Appearances by Compact Tensorial Representations (CVPR 2025 · similarity 0.89)
- HERA: Hybrid Explicit Representation for Ultra-Realistic Head Avatars (CVPR 2025 · similarity 0.89)
- RGBAvatar: Reduced Gaussian Blendshapes for Online Modeling of Head Avatars (CVPR 2025 · similarity 0.89)
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.
