InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interaction

doi:doi:10.57702/41vgeski

InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interaction

Text-conditioned human motion generation has experienced significant advancements with diffusion models trained on extensive motion capture data and corresponding textual annotations. However, extending such success to 3D dynamic human-object interaction (HOI) generation faces notable challenges, primarily due to the lack of large-scale interaction data and comprehensive descriptions that align with these interactions.

BibTex:

@dataset{Sirui_Xu_and_Ziyin_Wang_and_Yu-Xiong_Wang_and_Liang-Yan_Gui_2024,
    abstract = {Text-conditioned human motion generation has experienced significant advancements with diffusion models trained on extensive motion capture data and corresponding textual annotations. However, extending such success to 3D dynamic human-object interaction (HOI) generation faces notable challenges, primarily due to the lack of large-scale interaction data and comprehensive descriptions that align with these interactions.},
    author = {Sirui Xu and Ziyin Wang and Yu-Xiong Wang and Liang-Yan Gui},
    doi = {10.57702/41vgeski},
    institution = {No Organization},
    keyword = {'human-object interaction', 'text-to-3D', 'zero-shot learning'},
    month = {dec},
    publisher = {TIB},
    title = {InterDreamer: Zero-Shot Text to 3D Dynamic Human-Object Interaction},
    url = {https://service.tib.eu/ldmservice/dataset/interdreamer--zero-shot-text-to-3d-dynamic-human-object-interaction},
    year = {2024}
}