Research map / 3D vision / Face and shape
GETAvatar: Generative Textured Meshes for Animatable Human Avatars
Xuanmeng Zhang, Jianfeng Zhang, Rohan Chacko, Hongyi Xu, Guoxian Song, Yi Yang, Jiashi 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 SMPL template geometry prior to SDF prediction (ablation) | GETAvatar · THUman2.0 | FID_normal: 29.52 -> 22.31 | Improved |
| add gradient-based normal field (ablation) | GETAvatar · THUman2.0 | FID_normal: 63.49 -> 22.31 | Improved |
| use gradient-based normals instead of MLP-predicted normals (ablation) | GETAvatar · THUman2.0 | FID_normal: 89.38 -> 22.31 | Improved |
| add gradient-based normal field (ablation) | GETAvatar · THUman2.0 | FID_RGB: 20.23 -> 13.54 | Improved |
| add SMPL template prior to SDF (ablation) | GETAvatar · THUman2.0 | PCK: 99.47 -> 99.61 | No clear effect |
| use GETAvatar explicit mesh generation instead of GNARF | animatable human generation · THUman2.0 | FPS: 8 -> 17 | Improved |
| increase resolution from 512^2 to 1024^2 | GETAvatar · THUman2.0 | FID_normal: 22.31 -> 55.02 | Hurt |
| pretrain on THUman2.0 with normal maps then fine-tune on DeepFashion | GETAvatar · DeepFashion | geometry quality (qualitative) | Improved |
Later papers that compared with this method
2 later accepted papers report GetAvatar as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- Generative Human Geometry Distribution (ICLR 2026 · better on 3 of 3 shared results)
- Human Geometry Distribution for 3D Animation Generation (CVPR 2026 · better on 1 of 1 shared result)
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.
- GET3D — GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images (NeurIPS 2022) · 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
- DreamHuman: Animatable 3D Avatars from Text (NeurIPS 2023 · similarity 0.91)
- En3D: An Enhanced Generative Model for Sculpting 3D Humans from 2D Synthetic Data (CVPR 2024 · similarity 0.90)
- DreamAvatar: Text-and-Shape Guided 3D Human Avatar Generation via Diffusion Models (CVPR 2024 · similarity 0.89)
- 3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting (CVPR 2024 · similarity 0.88)
- AvatarVerse: High-Quality & Stable 3D Avatar Creation from Text and Pose (AAAI 2024 · similarity 0.88)
- CtrlAvatar: Controllable Avatars Generation via Disentangled Invertible Networks (AAAI 2025 · 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.
