ShapeLLM-Omni: A Native Multimodal LLM for 3D Generation and Understanding
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912409581518848 |
|---|---|
| author | Ye, Junliang Wang, Zhengyi Zhao, Ruowen Xie, Shenghao Zhu, Jun |
| author_facet | Ye, Junliang Wang, Zhengyi Zhao, Ruowen Xie, Shenghao Zhu, Jun |
| contents | Recently, the powerful text-to-image capabilities of ChatGPT-4o have led to growing appreciation for native multimodal large language models. However, its multimodal capabilities remain confined to images and text. Yet beyond images, the ability to understand and generate 3D content is equally crucial. To address this gap, we propose ShapeLLM-Omni-a native 3D large language model capable of understanding and generating 3D assets and text in any sequence. First, we train a 3D vector-quantized variational autoencoder (VQVAE), which maps 3D objects into a discrete latent space to achieve efficient and accurate shape representation and reconstruction. Building upon the 3D-aware discrete tokens, we innovatively construct a large-scale continuous training dataset named 3D-Alpaca, encompassing generation, comprehension, and editing, thus providing rich resources for future research and training. Finally, by performing instruction-based training of the Qwen-2.5-vl-7B-Instruct model on the 3D-Alpaca dataset. Our work provides an effective attempt at extending multimodal models with basic 3D capabilities, which contributes to future research in 3D-native AI. Project page: https://github.com/JAMESYJL/ShapeLLM-Omni |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_01853 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ShapeLLM-Omni: A Native Multimodal LLM for 3D Generation and Understanding Ye, Junliang Wang, Zhengyi Zhao, Ruowen Xie, Shenghao Zhu, Jun Computer Vision and Pattern Recognition Recently, the powerful text-to-image capabilities of ChatGPT-4o have led to growing appreciation for native multimodal large language models. However, its multimodal capabilities remain confined to images and text. Yet beyond images, the ability to understand and generate 3D content is equally crucial. To address this gap, we propose ShapeLLM-Omni-a native 3D large language model capable of understanding and generating 3D assets and text in any sequence. First, we train a 3D vector-quantized variational autoencoder (VQVAE), which maps 3D objects into a discrete latent space to achieve efficient and accurate shape representation and reconstruction. Building upon the 3D-aware discrete tokens, we innovatively construct a large-scale continuous training dataset named 3D-Alpaca, encompassing generation, comprehension, and editing, thus providing rich resources for future research and training. Finally, by performing instruction-based training of the Qwen-2.5-vl-7B-Instruct model on the 3D-Alpaca dataset. Our work provides an effective attempt at extending multimodal models with basic 3D capabilities, which contributes to future research in 3D-native AI. Project page: https://github.com/JAMESYJL/ShapeLLM-Omni |
| title | ShapeLLM-Omni: A Native Multimodal LLM for 3D Generation and Understanding |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.01853 |