Research map / 3D vision / Face and shape
gDNA: Towards Generative Detailed Neural Avatars
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 adversarial training to detailed normal modeling (ablation) | gDNA · Generated 3D shapes | FID: 42.18 -> 11.54 | Helped |
| Model shapes in canonical space and learn articulation, rather than directly generating posed shapes (ablation) | gDNA · Generated 3D shapes | FID: 43.80 -> 11.54 | Helped |
| Add detailed normal modeling and adversarial training rather than using coarse shape modeling alone (ablation) | gDNA · Generated 3D shapes | FID: 29.34 -> 11.54 | Helped |
| Fit gDNA rather than NPMs | SIZER · SIZER | Pred-to-Scan: 0.0156 -> 0.0134 | Helped |
| Fit gDNA rather than NPMs | SIZER · SIZER | Scan-to-Pred: 0.0215 -> 0.0123 | Helped |
| Fit gDNA rather than SMPLicit | SIZER · SIZER | Scan-to-Pred: 0.0240 -> 0.0123 | Helped |
Closest papers by meaning
- Design2Cloth: 3D Cloth Generation from 2D Masks (CVPR 2024 · similarity 0.91)
- SCULPT: Shape-Conditioned Unpaired Learning of Pose-dependent Clothed and Textured Human Meshes (CVPR 2024 · similarity 0.90)
- DAGSM: Disentangled Avatar Generation with GS-enhanced Mesh (CVPR 2025 · similarity 0.90)
- FreeCloth: Free-form Generation Enhances Challenging Clothed Human Modeling (CVPR 2025 · similarity 0.89)
- FRESA: Feedforward Reconstruction of Personalized Skinned Avatars from Few Images (CVPR 2025 · similarity 0.88)
- En3D: An Enhanced Generative Model for Sculpting 3D Humans from 2D Synthetic Data (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.