Research map / 3D vision / Face and shape
MoGA: 3D Generative Avatar Prior for Monocular Gaussian Avatar Reconstruction
Zijian Dong, Longteng Duan, Jie Song, Michael J. Black, Andreas Geiger
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 generative-prior-based latent initialization (instead of random) (ablation) | MoGA · CustomHumans | PSNR: 22.6996 -> 23.4383 | Improved |
| add generative-prior-based latent initialization (instead of random) (ablation) | MoGA · CustomHumans | LPIPS: 0.0891 -> 0.0791 | Improved |
| add generative-prior-based latent initialization (instead of random) (ablation) | MoGA · CustomHumans | SSIM: 0.9278 -> 0.9351 | Improved |
| add generative avatar prior (decoder and latent diffusion regularization) (ablation) | MoGA · CustomHumans | PSNR: 22.5838 -> 23.4383 | Improved |
| add generative avatar prior (decoder and latent diffusion regularization) (ablation) | MoGA · CustomHumans | SSIM: 0.9288 -> 0.9351 | Improved |
| add generative avatar prior (decoder and latent diffusion regularization) (ablation) | MoGA · CustomHumans | LPIPS: 0.0863 -> 0.0791 | Improved |
| MoGA versus PSHuman, strongest baseline | single-image Gaussian avatar reconstruction · THuman2.1 | PSNR: 19.9595 -> 24.0926 | Improved |
| MoGA versus PSHuman, strongest baseline | single-image Gaussian avatar reconstruction · CustomHumans | P2S: 1.4695 -> 1.4821 | Hurt |
| MoGA versus PSHuman, strongest baseline | single-image Gaussian avatar reconstruction · CustomHumans | PSNR: 18.6704 -> 23.4383 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- PSHuman — PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing (CVPR 2025) · better on 10 of 11 shared results
- SIFU — SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction (CVPR 2024) · better on 6 of 6 shared results
- SiTH — SiTH: Single-view Textured Human Reconstruction with Image-Conditioned Diffusion (CVPR 2024) · better on 6 of 6 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
- Human-3Diffusion: Realistic Avatar Creation via Explicit 3D Consistent Diffusion Models (NeurIPS 2024 · similarity 0.91)
- GAF: Gaussian Avatar Reconstruction from Monocular Videos via Multi-view Diffusion (CVPR 2025 · similarity 0.90)
- 3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting (CVPR 2024 · similarity 0.90)
- Synthetic Prior for Few-Shot Drivable Head Avatar Inversion (CVPR 2025 · similarity 0.89)
- 3D²-Actor: Learning Pose-Conditioned 3D-Aware Denoiser for Realistic Gaussian Avatar Modeling (AAAI 2025 · similarity 0.89)
- AniGS: Animatable Gaussian Avatar from a Single Image with Inconsistent Gaussian Reconstruction (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.
