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

TL;DR

This paper introduces a novel framework for explicit emotion control in 3D head avatars, allowing independent manipulation of emotion, geometry, and appearance in a feed-forward, single-image reconstruction pipeline.

Contribution

It proposes a dual-path modulation mechanism for emotion control, disentangling emotion from geometry and appearance, and introduces a new emotion-consistent multi-identity dataset.

Findings

Framework enables controllable emotion transfer and smooth interpolation.

Preserves reconstruction and reenactment fidelity across multiple backbones.

Disentangles emotion from speech-driven articulation and identity cues.

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.