Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Mughal, Muhammad Hamza, Dabral, Rishabh, Habibie, Ikhsanul, Donatelli, Lucia, Habermann, Marc, Theobalt, Christian
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2403.17936
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914729839034368
author Mughal, Muhammad Hamza
Dabral, Rishabh
Habibie, Ikhsanul
Donatelli, Lucia
Habermann, Marc
Theobalt, Christian
author_facet Mughal, Muhammad Hamza
Dabral, Rishabh
Habibie, Ikhsanul
Donatelli, Lucia
Habermann, Marc
Theobalt, Christian
contents Gestures play a key role in human communication. Recent methods for co-speech gesture generation, while managing to generate beat-aligned motions, struggle generating gestures that are semantically aligned with the utterance. Compared to beat gestures that align naturally to the audio signal, semantically coherent gestures require modeling the complex interactions between the language and human motion, and can be controlled by focusing on certain words. Therefore, we present ConvoFusion, a diffusion-based approach for multi-modal gesture synthesis, which can not only generate gestures based on multi-modal speech inputs, but can also facilitate controllability in gesture synthesis. Our method proposes two guidance objectives that allow the users to modulate the impact of different conditioning modalities (e.g. audio vs text) as well as to choose certain words to be emphasized during gesturing. Our method is versatile in that it can be trained either for generating monologue gestures or even the conversational gestures. To further advance the research on multi-party interactive gestures, the DnD Group Gesture dataset is released, which contains 6 hours of gesture data showing 5 people interacting with one another. We compare our method with several recent works and demonstrate effectiveness of our method on a variety of tasks. We urge the reader to watch our supplementary video at our website.
format Preprint
id arxiv_https___arxiv_org_abs_2403_17936
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ConvoFusion: Multi-Modal Conversational Diffusion for Co-Speech Gesture Synthesis
Mughal, Muhammad Hamza
Dabral, Rishabh
Habibie, Ikhsanul
Donatelli, Lucia
Habermann, Marc
Theobalt, Christian
Computer Vision and Pattern Recognition
Gestures play a key role in human communication. Recent methods for co-speech gesture generation, while managing to generate beat-aligned motions, struggle generating gestures that are semantically aligned with the utterance. Compared to beat gestures that align naturally to the audio signal, semantically coherent gestures require modeling the complex interactions between the language and human motion, and can be controlled by focusing on certain words. Therefore, we present ConvoFusion, a diffusion-based approach for multi-modal gesture synthesis, which can not only generate gestures based on multi-modal speech inputs, but can also facilitate controllability in gesture synthesis. Our method proposes two guidance objectives that allow the users to modulate the impact of different conditioning modalities (e.g. audio vs text) as well as to choose certain words to be emphasized during gesturing. Our method is versatile in that it can be trained either for generating monologue gestures or even the conversational gestures. To further advance the research on multi-party interactive gestures, the DnD Group Gesture dataset is released, which contains 6 hours of gesture data showing 5 people interacting with one another. We compare our method with several recent works and demonstrate effectiveness of our method on a variety of tasks. We urge the reader to watch our supplementary video at our website.
title ConvoFusion: Multi-Modal Conversational Diffusion for Co-Speech Gesture Synthesis
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.17936