Research map / 3D vision / Face and shape
XAGen: 3D Expressive Human Avatars Generation
Read the paperCheck 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 |
|---|---|---|---|
| Use XAGen rather than AvatarGen | human avatar generation · DeepFashion | FID: 9.53 -> 8.55 | Helped |
| Use XAGen rather than AvatarGen | human avatar generation · MPV | PCKf: 45.26 -> 63.77 | Helped |
| Use XAGen rather than AvatarGen | human avatar generation · UBC | FIDf: 13.23 -> 9.82 | Helped |
| Use XAGen rather than AvatarGen | human avatar generation · SHHQ | FID: 10.52 -> 5.88 | Helped |
| Add both face and hand Tri-planes (ablation) | XAGen · SHHQ | FID: 11.50 -> 5.88 | Helped |
| Add independent face rendering (ablation) | XAGen · SHHQ | FIDf: 20.63 -> 10.06 | Helped |
| Add independent face rendering (ablation) | XAGen · SHHQ | Exp: 6.58 -> 5.56 | Helped |
| Add face discriminator (ablation) | XAGen · SHHQ | FID: 7.40 -> 5.88 | Helped |
| Add face discriminator (ablation) | XAGen · SHHQ | Exp: 6.27 -> 5.56 | Helped |
| Add independent hand rendering (ablation) | XAGen · SHHQ | FIDh: 26.66 -> 19.23 | Helped |
| Add independent hand rendering (ablation) | XAGen · SHHQ | Hand: 4.51 -> 3.33 | Helped |
| Add hand discriminator (ablation) | XAGen · SHHQ | FIDh: 16.74 -> 19.23 | Helped |
Closest papers by meaning
- Expressive Gaussian Human Avatars from Monocular RGB Video (NeurIPS 2024 · similarity 0.87)
- AvatarVerse: High-Quality & Stable 3D Avatar Creation from Text and Pose (AAAI 2024 · similarity 0.87)
- En3D: An Enhanced Generative Model for Sculpting 3D Humans from 2D Synthetic Data (CVPR 2024 · similarity 0.86)
- Morphable Diffusion: 3D-Consistent Diffusion for Single-image Avatar Creation (CVPR 2024 · similarity 0.86)
- CtrlAvatar: Controllable Avatars Generation via Disentangled Invertible Networks (AAAI 2025 · similarity 0.86)
- SimAvatar: Simulation-Ready Avatars with Layered Hair and Clothing (CVPR 2025 · similarity 0.86)
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.