Giving Faces Their Feelings Back: Explicit Emotion Control for Feedforward Single-Image 3D Head Avatars

arXiv:2604.14541v1 Announce Type: new Abstract: We present a framework for explicit emotion control in feed-forward, single-image 3D head avatar reconstruction. Unlike existing pipelines where emotion is implicitly entangled with geometry or appearance, we treat emotion as a first-class control signal that can be manipulated independently and consistently across identities. Our method injects emotion into existing feed-forward architectures via a dual-path modulation mechanism without modifying their core design. Geometry modulation performs emotion-conditioned normalization in the original parametric space, disentangling emotional state from speech-driven articulation, while appearance modulation captures identity-aware, emotion-dependent visual cues beyond geometry. To enable learning under this setting, we construct a time-synchronized, emotion-consistent multi-identity dataset by transferring aligned emotional dynamics across identities. Integrated into multiple state-of-the-art backbones, our framework preserves reconstruction and reenactment fidelity while enabling controllable emotion transfer, disentangled manipulation, and smooth emotion interpolation, advancing expressive and scalable 3D head avatars.

Related

• Any3DAvatar: Fast and High-Quality Full-Head 3D Avatar Reconstruction from Single Portrait Image
• One-shot Compositional 3D Head Avatars with Deformable Hair
• Real-Time Human Reconstruction and Animation using Feed-Forward Gaussian Splatting
• Structure-Aware Fine-Grained Gaussian Splatting for Expressive Avatar Reconstruction
• Representing 3D Faces with Learnable B-Spline Volumes
• 3DRealHead: Few-Shot Detailed Head Avatar

Source: arXiv cs.CV | 2026-04-17