Orthogonal Spatial-temporal Distributional Transfer for 4D Generation
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (9) · 7287-7295
DOI: 10.1609/aaai.v40i9.37666 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Wei Liu und 6 weiteren Autor:innen.
Abstract (Originalsprache)
In the AIGC era, generating high-quality 4D content has garnered increasing research attention. Unfortunately, current 4D synthesis research is severely constrained by the lack of large-scale 4D datasets, preventing models from adequately learning the critical spatial-temporal features necessary for high-quality 4D generation, thus hindering progress in this domain. To combat this, we propose a novel framework that transfers rich spatial priors from existing 3D diffusion models and temporal priors from video diffusion models to enhance 4D synthesis. We develop a spatial-temporal-disentangled 4D (STD-4D) Diffusion model, which synthesizes 4D-aware videos through disentangled spatial and temporal latents. To facilitate the best feature transfer, we design a novel Orthogonal Spatial-temporal Distributional Transfer (Orster) mechanism, where the spatiotemporal feature distributions are carefully modeled and injected into the STD-4D Diffusion. Further, during the 4D construction, we devise a spatial-temporal-aware HexPlane (ST-HexPlane) to integrate the transferred spatiotemporal features for better 4D deformation and 4D Gaussian feature modeling. Experiments demonstrate that our method significantly outperforms existing approaches, achieving superior spatial-temporal consistency and higher-quality 4D synthesis.
Zitieren
APA
Liu, W., Wu, S., Li, B., Zhao, H., Fei, H., Lee, M., & Hsu, W. (2026). Orthogonal Spatial-temporal Distributional Transfer for 4D Generation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(9), 7287-7295. https://doi.org/10.1609/aaai.v40i9.37666
Vancouver
Liu W, Wu S, Li B, Zhao H, Fei H, Lee M, et al. Orthogonal Spatial-temporal Distributional Transfer for 4D Generation. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(9):7287-7295. doi:10.1609/aaai.v40i9.37666
BibTeX
@article{Liu2026,
author = {Liu, Wei and Wu, Shengqiong and Li, Bobo and Zhao, Haoyu and Fei, Hao and Lee, Mong-Li and Hsu, Wynne},
title = {Orthogonal Spatial-temporal Distributional Transfer for 4D Generation},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {9},
pages = {7287--7295},
doi = {10.1609/aaai.v40i9.37666}
}
EUVIMED