Research map / 3D vision / Gaussian splatting
FastAvatar: Towards Unified and Fast 3D Avatar Reconstruction with Large Gaussian Reconstruction Transformers
Yue Wu, Xuanhong Chen, Yufan Wu, Wen Li, Yuxi Lu, Kairui Feng
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 global attention (ablation) | FastAvatar · Nersemble, 1 view | PSNR: 15.40 -> 20.31 | Improved |
| add GS fusion (ablation) | FastAvatar · Nersemble, 16 views | PSNR: 16.25 -> 22.04 | Improved |
| add sliced fusion loss (ablation) | FastAvatar · Nersemble, 16 views | PSNR: 20.62 -> 22.04 | Improved |
| add landmark tracking loss (ablation) | FastAvatar · Nersemble, 4 views | PSNR: 21.64 -> 21.86 | Improved |
| add Gaussian pruning (ablation) | FastAvatar · Nersemble, 4 views | PSNR / #GS: PSNR 21.67 -> 21.86; #GS 86.7K -> 42.8K | Mixed |
| add sliced fusion loss at 1 view (ablation) | FastAvatar · Nersemble, 1 view | PSNR: 20.47 -> 20.31 | Hurt |
| increase landmark noise in FLAME tracking from 1 px to 32 px (ablation) | FastAvatar · FLAME tracking robustness | PSNR: 22.50 -> 22.02 | No clear effect |
| use FastAvatar instead of LAM | FastAvatar · Nersemble | LPIPS: 0.1608 -> 0.1267 | Improved |
Later papers that compared with this method
1 later accepted paper reports FastAvatar as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- FFAvatar: Feed-Forward 4D Head Avatar Reconstruction from Arbitrary Images (ECCV 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 1 of 1 on most shared results.
- Arc2Avatar — Arc2Avatar: Generating Expressive 3D Avatars from a Single Image via ID Guidance (CVPR 2025) · better on 4 of 4 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
- GeoAvatar: Geometrically-Consistent Multi-Person Avatar Reconstruction from Sparse Multi-View Videos (CVPR 2025 · similarity 0.91)
- Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Prior (CVPR 2025 · similarity 0.89)
- 3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting (CVPR 2024 · similarity 0.89)
- 3D²-Actor: Learning Pose-Conditioned 3D-Aware Denoiser for Realistic Gaussian Avatar Modeling (AAAI 2025 · similarity 0.89)
- GAF: Gaussian Avatar Reconstruction from Monocular Videos via Multi-view Diffusion (CVPR 2025 · similarity 0.89)
- RGBAvatar: Reduced Gaussian Blendshapes for Online Modeling of Head Avatars (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.
