HiFi-Mesh: High-Fidelity Efficient 3D Mesh Generation via Compact Autoregressive Dependence
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917231148924928 |
|---|---|
| author | Li, Yanfeng Tan, Tao Gao, Qingquan Cao, Zhiwen liu, Xiaohong Sun, Yue |
| author_facet | Li, Yanfeng Tan, Tao Gao, Qingquan Cao, Zhiwen liu, Xiaohong Sun, Yue |
| contents | 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 $6\times$ 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_21314 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | HiFi-Mesh: High-Fidelity Efficient 3D Mesh Generation via Compact Autoregressive Dependence Li, Yanfeng Tan, Tao Gao, Qingquan Cao, Zhiwen liu, Xiaohong Sun, Yue Computer Vision and Pattern Recognition Graphics 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 $6\times$ 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. |
| title | HiFi-Mesh: High-Fidelity Efficient 3D Mesh Generation via Compact Autoregressive Dependence |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2601.21314 |