Auto-Regressive Diffusion for Generating 3D Human-Object Interactions
Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (3) · 3131-3139
DOI: 10.1609/aaai.v39i3.32322 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Zichen Geng und 3 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref).
Abstract (Originalsprache)
Text-driven Human-Object Interaction (Text-to-HOI) generation is an emerging field with applications in animation, video games, virtual reality, and robotics. A key challenge in HOI generation is maintaining interaction consistency in long sequences. Existing Text-to-Motion-based approaches, such as discrete motion tokenization, cannot be directly applied to HOI generation due to limited data in this domain and the complexity of the modality. To address the problem of interaction consistency in long sequences, we propose an autoregressive diffusion model (ARDHOI) that predicts the next continuous token. Specifically, we introduce a Contrastive Variational Autoencoder (cVAE) to learn a physically plausible space of continuous HOI tokens, thereby ensuring that generated human-object motions are realistic and natural. For generating sequences autoregressively, we develop a Mamba-based context encoder to capture and maintain consistent sequential actions. Additionally, we implement an MLP-based denoiser to generate the subsequent token conditioned on the encoded context. Our model has been evaluated on the OMOMO and BEHAVE datasets, where it outperforms existing state-of-the-art methods in terms of both performance and inference speed. This makes ARDHOI a robust and efficient solution for text-driven HOI tasks.
Zitieren
APA
Geng, Z., Hayder, Z., Liu, W., & Mian, A. S. (2025). Auto-Regressive Diffusion for Generating 3D Human-Object Interactions. Proceedings of the AAAI Conference on Artificial Intelligence, 39(3), 3131-3139. https://doi.org/10.1609/aaai.v39i3.32322
Vancouver
Geng Z, Hayder Z, Liu W, Mian AS. Auto-Regressive Diffusion for Generating 3D Human-Object Interactions. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(3):3131-3139. doi:10.1609/aaai.v39i3.32322
BibTeX
@article{Geng2025,
author = {Geng, Zichen and Hayder, Zeeshan and Liu, Wei and Mian, Ajmal Saeed},
title = {Auto-Regressive Diffusion for Generating 3D Human-Object Interactions},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2025},
volume = {39},
number = {3},
pages = {3131--3139},
doi = {10.1609/aaai.v39i3.32322}
}
EUVIMED