Research map / 3D vision / Face and shape
Anti-Avatar: Protect Against Unauthorized 3D Head Avatar Generation via Dual-Space Divergence
Lingzhuang Meng, Mingwen Shao, Xiang Lv, Mengyao Wu, Yuanjian Qiao, Jie Zhang
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 geometric disruption loss (ablation) | Anti-Avatar · avatar protection | qualitative | Improved |
| add perceptual confusion loss (ablation) | Anti-Avatar · avatar protection | qualitative | Improved |
| Anti-Avatar vs AdvPaint on identity | Anti-Avatar · CelebA-HQ self-reenactment | ISM (lower better): 0.2923 -> 0.2175 | Improved |
| Anti-Avatar vs FaceLock on face detection rate | Anti-Avatar · CelebA-HQ self-reenactment | FDR (lower better): 1.0000 -> 0.8328 | Improved |
| Anti-Avatar vs AdvPaint on FID | Anti-Avatar · CelebA-HQ self-reenactment | FID (higher better): 113.13 -> 116.84 | Improved |
| Anti-Avatar vs AdvPaint on FID | Anti-Avatar · VFHQ cross-reenactment | FID (higher better): 111.95 -> 112.28 | No clear effect |
| apply to LAM instead of GAGAvatar | Anti-Avatar · CelebA-HQ self-reenactment | ISM: 0.2175 (GAGAvatar) vs 0.5636 (LAM) | Mixed |
Closest papers by meaning
- High-Fidelity 3D Head Avatars Reconstruction through Spatially-Varying Expression Conditioned Neural Radiance Field (AAAI 2024 · similarity 0.87)
- Arc2Avatar: Generating Expressive 3D Avatars from a Single Image via ID Guidance (CVPR 2025 · similarity 0.85)
- AvatarVerse: High-Quality & Stable 3D Avatar Creation from Text and Pose (AAAI 2024 · similarity 0.85)
- PEGASUS: Personalized Generative 3D Avatars with Composable Attributes (CVPR 2024 · similarity 0.84)
- UltrAvatar: A Realistic Animatable 3D Avatar Diffusion Model with Authenticity Guided Textures (CVPR 2024 · similarity 0.84)
- CAP4D: Creating Animatable 4D Portrait Avatars with Morphable Multi-View Diffusion Models (CVPR 2025 · similarity 0.84)
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.
