Hierarchical Structured Latents for Efficient 3D Generation
ACM Transactions on Graphics · 09.11.2026 · 45 (6) · 1-13
DOI: 10.1145/3842496 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Graphics, online erschienen am 09.11.2026. Verfasst von Yuxuan Xiong und 5 weiteren Autor:innen. Die Arbeit nennt 79 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Commission of Shanghai Municipality, Guangdong Laboratory of Artificial Intelligence and Digital Economy, Shanghai Municipal Commission of Economy and Informatization.
Abstract (Originalsprache)
Generating high-fidelity 3D geometry from a single image remains a challenge due to the complex trade-off between representation capacity and computational efficiency. Existing methods often employ uniform latent distributions, which lack the flexibility to allocate resources according to local geometric complexity. In this paper, we utilize a two-stage framework for image-conditioned 3D generation based on a multi-scale latent representation. Our approach decomposes the generation process into the creation of a multi-scale spatial structure followed by the synthesis of fine-grained surface details. To ensure structural integrity, we introduce a generation-friendly octree reparameterization that utilizes a top-down masking rule to guarantee spatial exclusivity and completeness by construction, effectively bypassing the need for generative models to learn hard structural constraints. Furthermore, we propose Scale-Modulated Positional Embedding (SMPE), which adaptively adjusts the frequency bandwidth of positional encodings based on the local latent scale. This allows transformers to dynamically aggregate global context for coarse regions and localized details for complex areas. Extensive experiments demonstrate that our method achieves superior reconstruction fidelity and generation quality, offering a more efficient and adaptive solution for high-resolution 3D asset creation. Code for this paper is at https://github.com/XiongYX0817/HSL-3D.
Förderung
- Science and Technology Commission of Shanghai Municipality
- Guangdong Laboratory of Artificial Intelligence and Digital Economy
- Shanghai Municipal Commission of Economy and Informatization
Zitieren
APA
Xiong, Y., Dou, Y., Shi, R., Wang, T., Zhang, C., & Ni, B. (2026). Hierarchical Structured Latents for Efficient 3D Generation. ACM Transactions on Graphics, 45(6), 1-13. https://doi.org/10.1145/3842496
Vancouver
Xiong Y, Dou Y, Shi R, Wang T, Zhang C, Ni B. Hierarchical Structured Latents for Efficient 3D Generation. ACM Transactions on Graphics. 2026;45(6):1-13. doi:10.1145/3842496
BibTeX
@article{Xiong2026,
author = {Xiong, Yuxuan and Dou, Yishun and Shi, Rui and Wang, Tielong and Zhang, Chang and Ni, Bingbing},
title = {Hierarchical Structured Latents for Efficient 3D Generation},
journal = {ACM Transactions on Graphics},
year = {2026},
volume = {45},
number = {6},
pages = {1--13},
doi = {10.1145/3842496}
}
EUVIMED