Research map / 3D vision / 3D generation
Multi-view Consistent 3D Gaussian Head Avatars 'without' Multi-view Generation
Aviral Chharia, Fernando De la Torre
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 SE(3) Multi-view Critic loss (ablation) | MVCHead · FFHQ-C | FID: 5.41 -> 3.94 | Improved |
| add SE(3) Multi-view Critic loss (ablation) | MVCHead · FFHQ-C | MEt3R: 0.3144 -> 0.2620 | Improved |
| add HiSS state space block (ablation) | MVCHead · FFHQ-C | FID: 5.28 -> 3.94 | Improved |
| add HiSS state space block (ablation) | MVCHead · FFHQ-C | MEt3R: 0.2948 -> 0.2620 | Improved |
| use HiBiSS bidirectional scan instead of unidirectional (ablation) | MVCHead · FFHQ-C | FID: 4.78 -> 3.94 | Improved |
| use HiBiSS bidirectional scan instead of unidirectional (ablation) | MVCHead · FFHQ-C | MEt3R: 0.2873 -> 0.2620 | Improved |
| add adversarial texture loss (ablation) | MVCHead · FFHQ-C | training stability: collapse | Improved |
| MVCHead vs CGSGAN on cross-view texture consistency | MVCHead · Multi-view consistency (100 avatars) | cLPIPS: 0.0622 -> 0.0528 | Improved |
| MVCHead vs CGSGAN on geometric consistency | MVCHead · Multi-view consistency (100 avatars) | MEt3R: 0.2814 -> 0.2620 | Improved |
| MVCHead vs CGSGAN on depth error | MVCHead · Multi-view consistency (100 avatars) | depth error: 6.6624 vs 6.6649 | No clear effect |
| MVCHead vs CGSGAN on shape consistency | MVCHead · Multi-view consistency (100 avatars) | Chamfer distance: 0.6724 -> 0.6654 | Improved |
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.
- CGSGAN — CGS-GAN: 3D Consistent Gaussian Splatting GANs for High Resolution Human Head Synthesis (NeurIPS 2025) · better on 9 of 10 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 0.91)
- GPAvatar: High-fidelity Head Avatars by Learning Efficient Gaussian Projections (CVPR 2025 · similarity 0.90)
- 3D Gaussian Head Avatars with Expressive Dynamic Appearances by Compact Tensorial Representations (CVPR 2025 · similarity 0.90)
- Gaussian Eigen Models for Human Heads (CVPR 2025 · similarity 0.90)
- MeGA: Hybrid Mesh-Gaussian Head Avatar for High-Fidelity Rendering and Head Editing (CVPR 2025 · similarity 0.90)
- GAF: Gaussian Avatar Reconstruction from Monocular Videos via Multi-view Diffusion (CVPR 2025 · similarity 0.89)
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.
