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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gong, Yicheng, Zhang, Jiawei, Liu, Liqiang, Wang, Yanwen, Chu, Lei, Li, Jiahao, Pan, Hao, Zhu, Hao, Lu, Yan
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917412822056960
author Gong, Yicheng
Zhang, Jiawei
Liu, Liqiang
Wang, Yanwen
Chu, Lei
Li, Jiahao
Pan, Hao
Zhu, Hao
Lu, Yan
author_facet Gong, Yicheng
Zhang, Jiawei
Liu, Liqiang
Wang, Yanwen
Chu, Lei
Li, Jiahao
Pan, Hao
Zhu, Hao
Lu, Yan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_14541
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Giving Faces Their Feelings Back: Explicit Emotion Control for Feedforward Single-Image 3D Head Avatars
Gong, Yicheng
Zhang, Jiawei
Liu, Liqiang
Wang, Yanwen
Chu, Lei
Li, Jiahao
Pan, Hao
Zhu, Hao
Lu, Yan
Computer Vision and Pattern Recognition
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.
title Giving Faces Their Feelings Back: Explicit Emotion Control for Feedforward Single-Image 3D Head Avatars
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.14541