Research map / 3D vision / Face and shape
PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360deg
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 PanoHead instead of EG3D | EG3D · FFHQ-F | FID-all: 6.2 -> 5.4 | Helped |
| Use PanoHead instead of EG3D | EG3D · FFHQ-F | ID: 0.74 -> 0.74 | No clear effect |
| Add foreground-aware tri-discrimination (ablation) | EG3D · FFHQ-F back poses | FID-back: 50.4 -> 44.1 | Helped |
| Add foreground-aware tri-discrimination (ablation) | EG3D · FFHQ-F back poses | IS-back: 4.3 -> 3.9 | Hurt |
| Use tri-grid instead of tri-plane (ablation) | EG3D + foreground-aware tri-discrimination · FFHQ-F back poses | FID-back: 44.1 -> 44.0 | Helped |
| Use tri-grid instead of tri-plane (ablation) | EG3D + foreground-aware tri-discrimination · FFHQ-F front poses | FID-front: 5.0 -> 5.5 | Hurt |
| Add camera self-adaptation (ablation) | EG3D + segmentation and tri-grid · FFHQ-F back poses | FID-back: 44.0 -> 40.9 | Helped |
| Add camera self-adaptation (ablation) | EG3D + segmentation and tri-grid · FFHQ-F front poses | FID-front: 5.5 -> 5.4 | Hurt |
| Add camera self-adaptation (ablation) | EG3D + segmentation and tri-grid · FFHQ-F all poses | FID-all: 5.2 -> 5.4 | Hurt |
| Add camera self-adaptation (ablation) | EG3D + segmentation and tri-grid · FFHQ-F back poses | IS-back: 4.2 -> 4.4 | Helped |
| Add camera self-adaptation (ablation) | EG3D + segmentation and tri-grid · FFHQ-F all poses | IS-all: 4.0 -> 4.1 | Helped |
| Add tri-grid and camera self-adaptation with foreground-aware discrimination (ablation) | EG3D · FFHQ-F back poses | FID-back: 50.4 -> 40.9 | Helped |
Closest papers by meaning
- CGS-GAN: 3D Consistent Gaussian Splatting GANs for High Resolution Human Head Synthesis (NeurIPS 2025 · similarity 0.90)
- Dual Encoder GAN Inversion for High-Fidelity 3D Head Reconstruction from Single Images (NeurIPS 2024 · similarity 0.90)
- What You See is What You GAN: Rendering Every Pixel for High-Fidelity Geometry in 3D GANs (CVPR 2024 · similarity 0.88)
- Synthetic Prior for Few-Shot Drivable Head Avatar Inversion (CVPR 2025 · similarity 0.87)
- In-N-Out: Faithful 3D GAN Inversion with Volumetric Decomposition for Face Editing (CVPR 2024 · similarity 0.87)
- HyPlaneHead: Rethinking Tri-plane-like Representations in Full-Head Image Synthesis (NeurIPS 2025 · similarity 0.87)
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.