AssetFormer: Modular 3D Assets Generation with Autoregressive Transformer
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_ | 1866911443473924096 |
|---|---|
| author | Zhu, Lingting Qian, Shengju Fan, Haidi Dong, Jiayu Jin, Zhenchao Zhou, Siwei Dong, Gen Wang, Xin Yu, Lequan |
| author_facet | Zhu, Lingting Qian, Shengju Fan, Haidi Dong, Jiayu Jin, Zhenchao Zhou, Siwei Dong, Gen Wang, Xin Yu, Lequan |
| contents | The digital industry demands high-quality, diverse modular 3D assets, especially for user-generated content~(UGC). In this work, we introduce AssetFormer, an autoregressive Transformer-based model designed to generate modular 3D assets from textual descriptions. Our pilot study leverages real-world modular assets collected from online platforms. AssetFormer tackles the challenge of creating assets composed of primitives that adhere to constrained design parameters for various applications. By innovatively adapting module sequencing and decoding techniques inspired by language models, our approach enhances asset generation quality through autoregressive modeling. Initial results indicate the effectiveness of AssetFormer in streamlining asset creation for professional development and UGC scenarios. This work presents a flexible framework extendable to various types of modular 3D assets, contributing to the broader field of 3D content generation. The code is available at https://github.com/Advocate99/AssetFormer. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_12100 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | AssetFormer: Modular 3D Assets Generation with Autoregressive Transformer Zhu, Lingting Qian, Shengju Fan, Haidi Dong, Jiayu Jin, Zhenchao Zhou, Siwei Dong, Gen Wang, Xin Yu, Lequan Computer Vision and Pattern Recognition The digital industry demands high-quality, diverse modular 3D assets, especially for user-generated content~(UGC). In this work, we introduce AssetFormer, an autoregressive Transformer-based model designed to generate modular 3D assets from textual descriptions. Our pilot study leverages real-world modular assets collected from online platforms. AssetFormer tackles the challenge of creating assets composed of primitives that adhere to constrained design parameters for various applications. By innovatively adapting module sequencing and decoding techniques inspired by language models, our approach enhances asset generation quality through autoregressive modeling. Initial results indicate the effectiveness of AssetFormer in streamlining asset creation for professional development and UGC scenarios. This work presents a flexible framework extendable to various types of modular 3D assets, contributing to the broader field of 3D content generation. The code is available at https://github.com/Advocate99/AssetFormer. |
| title | AssetFormer: Modular 3D Assets Generation with Autoregressive Transformer |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.12100 |