HiFi-Mesh: High-Fidelity Efficient 3D Mesh Generation via Compact Autoregressive Dependence
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (8) · 6566-6574
DOI: 10.1609/aaai.v40i8.37586 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Yanfeng Li und 5 weiteren Autor:innen.
Abstract (Originalsprache)
High-fidelity 3D meshes can be tokenized into one-dimension (1D) sequences and directly modeled using autoregressive approaches for faces and vertices. However, existing methods suffer from insufficient resource utilization, resulting in slow inference and the ability to handle only small-scale sequences, which severely constrains the expressible structural details. We introduce the Latent Autoregressive Network (LANE), which incorporates compact autoregressive dependencies in the generation process, achieving a 6× improvement in maximum generatable sequence length compared to existing methods. To further accelerate inference, we propose the Adaptive Computation Graph Reconfiguration (AdaGraph) strategy, which effectively overcomes the efficiency bottleneck of traditional serial inference through spatiotemporal decoupling in the generation process. Experimental validation demonstrates that LANE achieves superior performance across generation speed, structural detail, and geometric consistency, providing an effective solution for high-quality 3D mesh generation.
Zitieren
APA
Li, Y., Tan, T., Gao, Q., Cao, Z., Liu, X., & Sun, Y. (2026). HiFi-Mesh: High-Fidelity Efficient 3D Mesh Generation via Compact Autoregressive Dependence. Proceedings of the AAAI Conference on Artificial Intelligence, 40(8), 6566-6574. https://doi.org/10.1609/aaai.v40i8.37586
Vancouver
Li Y, Tan T, Gao Q, Cao Z, Liu X, Sun Y. HiFi-Mesh: High-Fidelity Efficient 3D Mesh Generation via Compact Autoregressive Dependence. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(8):6566-6574. doi:10.1609/aaai.v40i8.37586
BibTeX
@article{Li2026,
author = {Li, Yanfeng and Tan, Tao and Gao, Qinquan and Cao, Zhiwen and Liu, Xiaohong and Sun, Yue},
title = {HiFi-Mesh: High-Fidelity Efficient 3D Mesh Generation via Compact Autoregressive Dependence},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {8},
pages = {6566--6574},
doi = {10.1609/aaai.v40i8.37586}
}
EUVIMED