SS4D: Native 4D Generative Model via Structured Spacetime Latents
ACM Transactions on Graphics · 2025-12 · 44 (6) · 1-12
DOI: 10.1145/3763302 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Graphics, online erschienen am 04.12.2025. Verfasst von Zhibing Li und 5 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 51 Literaturangaben. Gefördert von: National Key R&D Program of China, Shanghai Artificial Intelligence Laboratory, Hong Kong RGC TRS.
Abstract (Originalsprache)
We present SS4D, a native 4D generative model that synthesizes dynamic 3D objects directly from monocular video. Unlike prior approaches that construct 4D representations by optimizing over 3D or video generative models, we train a generator directly on 4D data, achieving high fidelity, temporal coherence, and structural consistency. At the core of our method is a compressed set of structured spacetime latents. Specifically, (1) To address the scarcity of 4D training data, we build on a pre-trained single-image-to-3D model, preserving strong spatial consistency. (2) Temporal consistency is enforced by introducing dedicated temporal layers that reason across frames. (3) To support efficient training and inference over long video sequences, we compress the latent sequence along the temporal axis using factorized 4D convolutions and temporal downsampling blocks. In addition, we employ a carefully designed training strategy to enhance robustness against occlusion and motion blur, leading to high-quality generation. Extensive experiments show that SS4D produces spatio-temporally consistent 4D objects with superior quality and efficiency, significantly outperforming state-of-the-art methods on both synthetic and real-world datasets.
Förderung
- National Key R&D Program of China
- Shanghai Artificial Intelligence Laboratory
- Hong Kong RGC TRS
- the Centre for Perceptual and Interactive Intelligence (CPII) Ltd under the Innovation and Technology Commission (ITC)?s InnoHK
Zitieren
APA
Li, Z., Zhang, M., Wu, T., Tan, J., Wang, J., & Lin, D. (2025). SS4D: Native 4D Generative Model via Structured Spacetime Latents. ACM Transactions on Graphics, 44(6), 1-12. https://doi.org/10.1145/3763302
Vancouver
Li Z, Zhang M, Wu T, Tan J, Wang J, Lin D. SS4D: Native 4D Generative Model via Structured Spacetime Latents. ACM Transactions on Graphics. 2025;44(6):1-12. doi:10.1145/3763302
BibTeX
@article{Li2025,
author = {Li, Zhibing and Zhang, Mengchen and Wu, Tong and Tan, Jing and Wang, Jiaqi and Lin, Dahua},
title = {SS4D: Native 4D Generative Model via Structured Spacetime Latents},
journal = {ACM Transactions on Graphics},
year = {2025},
volume = {44},
number = {6},
pages = {1--12},
doi = {10.1145/3763302}
}
EUVIMED