SentiAvatar: Towards Expressive and Interactive Digital Humans

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jin, Chuhao, Zhang, Rui, Gao, Qingzhe, Shi, Haoyu, Wu, Dayu, Jiang, Yichen, Wu, Yihan, Song, Ruihua
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910145420722176
author Jin, Chuhao
Zhang, Rui
Gao, Qingzhe
Shi, Haoyu
Wu, Dayu
Jiang, Yichen
Wu, Yihan
Song, Ruihua
author_facet Jin, Chuhao
Zhang, Rui
Gao, Qingzhe
Shi, Haoyu
Wu, Dayu
Jiang, Yichen
Wu, Yihan
Song, Ruihua
contents We present SentiAvatar, a framework for building expressive interactive 3D digital humans, and use it to create SuSu, a virtual character that speaks, gestures, and emotes in real time. Achieving such a system remains challenging, as it requires jointly addressing three key problems: the lack of large-scale, high-quality multimodal data, robust semantic-to-motion mapping, and fine-grained frame-level motion-prosody synchronization. To solve these problems, first, we build SuSuInterActs (21K clips, 37 hours), a dialogue corpus captured via optical motion capture around a single character with synchronized speech, full-body motion, and facial expressions. Second, we pre-train a Motion Foundation Model on 200K+ motion sequences, equipping it with rich action priors that go well beyond the conversation. We then propose an audio-aware plan-then-infill architecture that decouples sentence-level semantic planning from frame-level prosody-driven interpolation, so that generated motions are both semantically appropriate and rhythmically aligned with speech. Experiments show that SentiAvatar achieves state-of-the-art on both SuSuInterActs (R@1 43.64%, nearly 2 times the best baseline) and BEATv2 (FGD 4.941, BC 8.078), producing 6s of output in 0.3s with unlimited multi-turn streaming. The source code, model, and dataset are available at https://sentiavatar.github.io.
format Preprint
id arxiv_https___arxiv_org_abs_2604_02908
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SentiAvatar: Towards Expressive and Interactive Digital Humans
Jin, Chuhao
Zhang, Rui
Gao, Qingzhe
Shi, Haoyu
Wu, Dayu
Jiang, Yichen
Wu, Yihan
Song, Ruihua
Computer Vision and Pattern Recognition
Human-Computer Interaction
Multimedia
We present SentiAvatar, a framework for building expressive interactive 3D digital humans, and use it to create SuSu, a virtual character that speaks, gestures, and emotes in real time. Achieving such a system remains challenging, as it requires jointly addressing three key problems: the lack of large-scale, high-quality multimodal data, robust semantic-to-motion mapping, and fine-grained frame-level motion-prosody synchronization. To solve these problems, first, we build SuSuInterActs (21K clips, 37 hours), a dialogue corpus captured via optical motion capture around a single character with synchronized speech, full-body motion, and facial expressions. Second, we pre-train a Motion Foundation Model on 200K+ motion sequences, equipping it with rich action priors that go well beyond the conversation. We then propose an audio-aware plan-then-infill architecture that decouples sentence-level semantic planning from frame-level prosody-driven interpolation, so that generated motions are both semantically appropriate and rhythmically aligned with speech. Experiments show that SentiAvatar achieves state-of-the-art on both SuSuInterActs (R@1 43.64%, nearly 2 times the best baseline) and BEATv2 (FGD 4.941, BC 8.078), producing 6s of output in 0.3s with unlimited multi-turn streaming. The source code, model, and dataset are available at https://sentiavatar.github.io.
title SentiAvatar: Towards Expressive and Interactive Digital Humans
topic Computer Vision and Pattern Recognition
Human-Computer Interaction
Multimedia
url https://arxiv.org/abs/2604.02908