Research map / 3D vision / Face and shape
Mind-to-Face: Neural-Driven Photorealistic Avatar Synthesis via EEG Decoding
Haolin Xiong, Tianwen Fu, Yunxuan Cai, Pratusha Prasad, Haiwei Chen, Wenbin Teng, Hanyuan Xiao, Yajie Zhao
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 |
|---|---|---|---|
| predict dense position maps instead of blendshape coefficients (ablation) | Mind-to-Face · EEG-to-face, Subject 1, Angry | mean point-to-surface error (mm): 1.0792 -> 0.4982 | Improved |
| predict dense position maps instead of blendshape coefficients (ablation) | Mind-to-Face · EEG-to-face, Subject 2, Angry | mean point-to-surface error (mm): 1.6492 -> 0.5534 | Improved |
| predict dense position maps instead of blendshape coefficients (ablation) | Mind-to-Face · EEG-to-face, EMOSTIM cross-trial | mean point-to-surface error (mm): Subject 1: 0.6838 -> 0.5158; Subject 2: 1.5078 -> 0.7077 | Improved |
| predict dense position maps instead of blendshape coefficients (ablation) | Mind-to-Face · EEG-to-face, Subject 1, Neutral | mean point-to-surface error (mm): 0.3270 -> 0.4028 | Hurt |
| predict dense position maps instead of blendshape coefficients (ablation) | Mind-to-Face · EEG-to-face, Subject 2, Neutral | mean point-to-surface error (mm): 1.3065 -> 0.3245 | Improved |
| predict dense position maps instead of blendshape coefficients (ablation) | Mind-to-Face · EEG-to-face, Subject 1, Disgust | vertices below 1 mm (%): 42.03 -> 61.89 | Improved |
| use own topology-consistent face tracking instead of GaussianAvatars FLAME/VHAP tracking (ablation) | Mind-to-Face avatar rendering · headcap-occluded capture with extreme expressions | render quality (qualitative) | Improved |
| use own tracking vs GaussianAvatars tracking in occlusion-free scenario (ablation) | Mind-to-Face avatar rendering · occlusion-free scenario | render quality (qualitative) | No clear effect |
Closest papers by meaning
- EMOPortraits: Emotion-enhanced Multimodal One-shot Head Avatars (CVPR 2024 · similarity 0.87)
- MoEE: Mixture of Emotion Experts for Audio-Driven Portrait Animation (CVPR 2025 · similarity 0.86)
- Neuro-3D: Towards 3D Visual Decoding from EEG Signals (CVPR 2025 · similarity 0.86)
- MindAlign: Bridging EEG, Vision, and Language for Zero-Shot Visual Decoding (NeurIPS 2026 · similarity 0.86)
- High-Fidelity 3D Head Avatars Reconstruction through Spatially-Varying Expression Conditioned Neural Radiance Field (AAAI 2024 · similarity 0.86)
- DiffusionAvatars: Deferred Diffusion for High-fidelity 3D Head Avatars (CVPR 2024 · similarity 0.85)
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.
