X2C: A Dataset Featuring Nuanced Facial Expressions for Realistic Humanoid Imitation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Li, Peizhen, Cao, Longbing, Wu, Xiao-Ming, Yang, Runze, Yu, Xiaohan
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912595054690304
author Li, Peizhen
Cao, Longbing
Wu, Xiao-Ming
Yang, Runze
Yu, Xiaohan
author_facet Li, Peizhen
Cao, Longbing
Wu, Xiao-Ming
Yang, Runze
Yu, Xiaohan
contents The ability to imitate realistic facial expressions is essential for humanoid robots engaged in affective human-robot communication. However, the lack of datasets containing diverse humanoid facial expressions with proper annotations hinders progress in realistic humanoid facial expression imitation. To address these challenges, we introduce X2C (Anything to Control), a dataset featuring nuanced facial expressions for realistic humanoid imitation. With X2C, we contribute: 1) a high-quality, high-diversity, large-scale dataset comprising 100,000 (image, control value) pairs. Each image depicts a humanoid robot displaying a diverse range of facial expressions, annotated with 30 control values representing the ground-truth expression configuration; 2) X2CNet, a novel human-to-humanoid facial expression imitation framework that learns the correspondence between nuanced humanoid expressions and their underlying control values from X2C. It enables facial expression imitation in the wild for different human performers, providing a baseline for the imitation task, showcasing the potential value of our dataset; 3) real-world demonstrations on a physical humanoid robot, highlighting its capability to advance realistic humanoid facial expression imitation. Code and Data: https://lipzh5.github.io/X2CNet/
format Preprint
id arxiv_https___arxiv_org_abs_2505_11146
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle X2C: A Dataset Featuring Nuanced Facial Expressions for Realistic Humanoid Imitation
Li, Peizhen
Cao, Longbing
Wu, Xiao-Ming
Yang, Runze
Yu, Xiaohan
Robotics
Artificial Intelligence
Human-Computer Interaction
The ability to imitate realistic facial expressions is essential for humanoid robots engaged in affective human-robot communication. However, the lack of datasets containing diverse humanoid facial expressions with proper annotations hinders progress in realistic humanoid facial expression imitation. To address these challenges, we introduce X2C (Anything to Control), a dataset featuring nuanced facial expressions for realistic humanoid imitation. With X2C, we contribute: 1) a high-quality, high-diversity, large-scale dataset comprising 100,000 (image, control value) pairs. Each image depicts a humanoid robot displaying a diverse range of facial expressions, annotated with 30 control values representing the ground-truth expression configuration; 2) X2CNet, a novel human-to-humanoid facial expression imitation framework that learns the correspondence between nuanced humanoid expressions and their underlying control values from X2C. It enables facial expression imitation in the wild for different human performers, providing a baseline for the imitation task, showcasing the potential value of our dataset; 3) real-world demonstrations on a physical humanoid robot, highlighting its capability to advance realistic humanoid facial expression imitation. Code and Data: https://lipzh5.github.io/X2CNet/
title X2C: A Dataset Featuring Nuanced Facial Expressions for Realistic Humanoid Imitation
topic Robotics
Artificial Intelligence
Human-Computer Interaction
url https://arxiv.org/abs/2505.11146