Research map / 3D vision / Face and shape
URHead: A Unified UV-Space Representation for Joint Mesh–3DGS Optimization in Head Avatars
Seonghak Lee, Junhee Cho, Jisoo Park, Min-Gyu Park, Jongmin Lee, Ju Yoon, Junseok Kwon
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 3DGS Gaussians on top of the mesh (ablation) | URHead · INSTA | PSNR: 33.60 -> 35.31 | Improved |
| add 3DGS Gaussians on top of the mesh (ablation) | URHead · INSTA | LPIPS: 0.057 -> 0.022 | Improved |
| add normal loss supervised by DAViD pseudo normals (ablation) | URHead · INSTA | PSNR: 34.45 -> 35.31 | Improved |
| add normal loss supervised by DAViD pseudo normals (ablation) | URHead · INSTA | LPIPS: 0.047 -> 0.022 | Improved |
| add occlusion-aware blending (ablation) | URHead · INSTA | PSNR: 33.63 -> 35.31 | Improved |
| add occlusion-aware blending (ablation) | URHead · INSTA | LPIPS: 0.045 -> 0.022 | Improved |
| add mesh-only L1 photometric term (0.2 weight) (ablation) | URHead · INSTA | PSNR: 34.90 -> 35.31 | Improved |
| add mesh-only L1 photometric term (0.2 weight) (ablation) | URHead · INSTA | LPIPS: 0.031 -> 0.022 | Improved |
| use adaptive instead of uniform Gaussian sampling when raising UV resolution (ablation) | URHead · INSTA | PSNR / LPIPS | Improved |
| replace RGBAvatar with URHead | INSTA avg · INSTA | PSNR: 34.1445 -> 35.1785 | Improved |
| replace RGBAvatar with URHead | INSTA avg · INSTA | LPIPS: 0.0251 -> 0.0149 | Improved |
| replace RGBAvatar with URHead | PointAvatar dataset avg · PointAvatar | PSNR: 28.4582 -> 28.1972 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 on most shared results.
- RGBAvatar — RGBAvatar: Reduced Gaussian Blendshapes for Online Modeling of Head Avatars (CVPR 2025) · better on 5 of 6 shared results
- FlashAvatar — FlashAvatar: High-fidelity Head Avatar with Efficient Gaussian Embedding (CVPR 2024) · better on 3 of 3 shared results
- GaussianAvatars — GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians (CVPR 2024) · better on 3 of 3 shared results
- SplattingAvatar — SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting (CVPR 2024) · better on 3 of 3 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
- Gaussian Head Avatar: Ultra High-fidelity Head Avatar via Dynamic Gaussians (CVPR 2024 · similarity 0.90)
- HERA: Hybrid Explicit Representation for Ultra-Realistic Head Avatars (CVPR 2025 · similarity 0.90)
- MeGA: Hybrid Mesh-Gaussian Head Avatar for High-Fidelity Rendering and Head Editing (CVPR 2025 · similarity 0.89)
- GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians (CVPR 2024 · similarity 0.89)
- High-Fidelity 3D Head Avatars Reconstruction through Spatially-Varying Expression Conditioned Neural Radiance Field (AAAI 2024 · similarity 0.89)
- Generalizable and Animatable Gaussian Head Avatar (NeurIPS 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.
