Research map / 3D vision / Face and shape
OneGT: One-Shot Geometry-Texture Neural Rendering for Head Avatars
Jinshu Chen, Bingchuan Li, Fan Zhang, Songtao Zhao, Qian He
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 adaptive trainable keypoint heatmap width (ablation) | OneGT · VFHQ (ablation) | PSNR: 19.1248 -> 33.1270 | Improved |
| add adaptive strategy (ablation) | OneGT · VFHQ (ablation) | SSIM: 0.6931 -> 0.8066 | Improved |
| add adaptive strategy (ablation) | OneGT · VFHQ (ablation) | FID: 89.0225 -> 53.3462 | Improved |
| add adaptive strategy (ablation) | OneGT · VFHQ (ablation) | AED: 0.7857 -> 0.6572 | Improved |
| add adaptive strategy (ablation) | OneGT · VFHQ (ablation) | APD: 0.0329 -> 0.0264 | Improved |
| add synthetic rendering data to training (ablation) | OneGT · VFHQ (ablation) | PSNR: 30.4812 -> 33.1270 | Improved |
| add synthetic rendering data (ablation) | OneGT · VFHQ (ablation) | SSIM: 0.7286 -> 0.8066 | Improved |
| add synthetic rendering data (ablation) | OneGT · VFHQ (ablation) | FID: 59.1253 -> 53.3462 | Improved |
| add synthetic rendering data (ablation) | OneGT · VFHQ (ablation) | AED: 0.7733 -> 0.6572 | Improved |
| add synthetic rendering data (ablation) | OneGT · VFHQ (ablation) | APD: 0.0352 -> 0.0264 | Improved |
Closest papers by meaning
- Realistic One-Shot Mesh-Based Head Avatars (ECCV 2022 · similarity 0.91)
- GeneAvatar: Generic Expression-Aware Volumetric Head Avatar Editing from a Single Image (CVPR 2024 · similarity 0.87)
- Efficient 3D Implicit Head Avatar with Mesh-anchored Hash Table Blendshapes (CVPR 2024 · similarity 0.87)
- MeGA: Hybrid Mesh-Gaussian Head Avatar for High-Fidelity Rendering and Head Editing (CVPR 2025 · similarity 0.87)
- High-Fidelity 3D Head Avatars Reconstruction through Spatially-Varying Expression Conditioned Neural Radiance Field (AAAI 2024 · similarity 0.86)
- Generalizable and Animatable Gaussian Head Avatar (NeurIPS 2024 · similarity 0.86)
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.
