Research map / 3D vision / NeRF and radiance fields
SphereHead: Stable 3D Full-head Synthesis with Spherical Tri-plane Representation
Heyuan Li, Ce Chen, Tianhao Shi, Yuda Qiu, Sizhe An, Guanying CHEN, Xiaoguang Han
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 |
|---|---|---|---|
| replace tri-grid with a single spherical tri-plane (ablation) | PanoHead-style generator · WildHead user study | fake face rate: 23.7% -> 3.7% | Improved |
| replace tri-grid with single sphere (ablation) | PanoHead-style generator · WildHead user study | high-quality rate: 26.1% -> 78.7% | Improved |
| add second orthogonal sphere (dual sphere) (ablation) | single-sphere SphereHead · WildHead user study | fake face rate: 3.7% -> 0.9% | Improved |
| add second sphere (ablation) | single-sphere SphereHead · WildHead | FID: 8.1 -> 7.9 | Improved |
| add view-image consistency (ViCo) loss to tri-grid (ablation) | PanoHead tri-grid · WildHead user study | fake face rate: 23.7% -> 4.8% | Improved |
| add ViCo loss to dual sphere (ablation) | dual-sphere SphereHead · WildHead user study | high-quality rate: 84.2% -> 90.4% | Improved |
| add ViCo loss to dual sphere (ablation) | dual-sphere SphereHead · WildHead | FID: 7.9 -> 7.9 | No clear effect |
| add parsing branch (ablation) | dual-sphere + ViCo · WildHead user study | high-quality rate: 90.4% -> 92.6% | Improved |
| add parsing branch (ablation) | dual-sphere + ViCo · WildHead | FID: 7.9 -> 7.8 | Improved |
| use SphereHead instead of PanoHead for single-view inversion | GAN inversion with PTI · FFHQ single-view inversion user study | preference share: 17.9% -> 82.1% | Improved |
| train PanoHead on the WildHead collection with more diverse hairstyles | PanoHead · random sampling | back-view quality | Mixed |
Later papers that compared with this method
1 later accepted paper reports SphereHead as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- PercHead: Perceptual Head Model for Single-Image 3D Head Reconstruction & Editing (CVPR 2026 · better on 4 of 4 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- PanoHead — PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360deg (CVPR 2023) · better on 4 of 4 shared results
- StyleSDF — StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generation (CVPR 2022) · better on 1 of 1 shared result
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
- HyPlaneHead: Rethinking Tri-plane-like Representations in Full-Head Image Synthesis (NeurIPS 2025 · similarity 0.92)
- CGS-GAN: 3D Consistent Gaussian Splatting GANs for High Resolution Human Head Synthesis (NeurIPS 2025 · similarity 0.89)
- Dual Encoder GAN Inversion for High-Fidelity 3D Head Reconstruction from Single Images (NeurIPS 2024 · similarity 0.88)
- In-N-Out: Faithful 3D GAN Inversion with Volumetric Decomposition for Face Editing (CVPR 2024 · similarity 0.86)
- DiffPortrait360: Consistent Portrait Diffusion for 360 View Synthesis (CVPR 2025 · similarity 0.86)
- G-NeRF: Geometry-enhanced Novel View Synthesis from Single-View Images (CVPR 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.
