Research map / 3D vision / Face and shape
Head360: Learning a Parametric 3D Full-Head for Free-View Synthesis in 360°
Yuxiao He, Yiyu Zhuang, Yanwen Wang, Yao Yao, Siyu Zhu, Xiaoyu Li, Qi Zhang, Xun Cao, Hao Zhu
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 |
|---|---|---|---|
| optimize neural texture instead of texture code, with shape fixed from landmarks, for single-image fitting | Head360 fitting · single-image fitting on SynHead100 | PSNR / SSIM / LPIPS / CSIM: PSNR 17.41 vs 17.18 (PanoHead re-trained) | Improved |
| use hex-planes instead of tri-planes (ablation) | Head360 representation · generated results | LPIPS (x0.01): 9.54 -> 7.31 (no-refine row) | Improved |
| use mesh + neural texture + hex-planes instead of conditioned vanilla NeRF (ablation) | Head360 representation · generated results | PSNR (dB): 24.44 -> 28.92 | Improved |
| add RefineNet (ablation) | Head360 · generated results | PSNR (dB) and LPIPS: PSNR 28.92 -> 28.27; LPIPS 7.31 -> 6.31 | Mixed |
| add hair detachment two-branch training (ablation) | Head360 · hair swapping | PSNR (dB): 20.04 -> 21.86 | Improved |
| add hair detachment two-branch training (ablation) | Head360 · hair swapping | LPIPS (x0.01): 15.89 -> 10.51 | Improved |
| optimize shape code and texture code simultaneously or iteratively with GAN inversion (ablation) | Head360 fitting · single-image fitting | fitting quality | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- MoFaNeRF — MoFaNeRF: Morphable Facial Neural Radiance Field (ECCV 2022) · better on 2 of 2 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
- 3D Gaussian Parametric Head Model (ECCV 2024 · similarity 0.91)
- MeGA: Hybrid Mesh-Gaussian Head Avatar for High-Fidelity Rendering and Head Editing (CVPR 2025 · similarity 0.89)
- DiffPortrait360: Consistent Portrait Diffusion for 360 View Synthesis (CVPR 2025 · similarity 0.89)
- FaceTalk: Audio-Driven Motion Diffusion for Neural Parametric Head Models (CVPR 2024 · similarity 0.88)
- LUCAS: Layered Universal Codec Avatars (CVPR 2025 · similarity 0.88)
- Efficient 3D Implicit Head Avatar with Mesh-anchored Hash Table Blendshapes (CVPR 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.
