Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.22858 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918452864745472 |
|---|---|
| author | Christiansen, Thor Vestergaard Pandey, Karran Reinders, Alba Singh, Karan Hannemose, Morten Rieger Bærentzen, J. Andreas |
| author_facet | Christiansen, Thor Vestergaard Pandey, Karran Reinders, Alba Singh, Karan Hannemose, Morten Rieger Bærentzen, J. Andreas |
| contents | We introduce Text Encoded Extrusions (TEE), a text-based representation that expresses mesh construction as sequences of face extrusions rather than polygon lists, and a method for generating 3D meshes from TEE using a large language model (LLM). By learning extrusion sequences that assemble a mesh, similar to the way artists create meshes, our approach naturally supports arbitrary output face counts and produces manifold meshes by design, in contrast to recent mesh generative transformer based models. The learnt extrusion sequences can also be applied to existing meshes - enabling editing in addition to generation. To train our model, we decompose a library of quadrilateral meshes with non-self-intersecting face loops into constituent loops, which can be viewed as their building blocks, and finetune an LLM on the steps for reassembling the quadrilateral meshes by performing a sequence of extrusions. We demonstrate that our representation enables reconstruction, novel shape synthesis, and the addition of new features to existing meshes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_22858 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Learning to Build Shapes by Extrusion Christiansen, Thor Vestergaard Pandey, Karran Reinders, Alba Singh, Karan Hannemose, Morten Rieger Bærentzen, J. Andreas Graphics Artificial Intelligence We introduce Text Encoded Extrusions (TEE), a text-based representation that expresses mesh construction as sequences of face extrusions rather than polygon lists, and a method for generating 3D meshes from TEE using a large language model (LLM). By learning extrusion sequences that assemble a mesh, similar to the way artists create meshes, our approach naturally supports arbitrary output face counts and produces manifold meshes by design, in contrast to recent mesh generative transformer based models. The learnt extrusion sequences can also be applied to existing meshes - enabling editing in addition to generation. To train our model, we decompose a library of quadrilateral meshes with non-self-intersecting face loops into constituent loops, which can be viewed as their building blocks, and finetune an LLM on the steps for reassembling the quadrilateral meshes by performing a sequence of extrusions. We demonstrate that our representation enables reconstruction, novel shape synthesis, and the addition of new features to existing meshes. |
| title | Learning to Build Shapes by Extrusion |
| topic | Graphics Artificial Intelligence |
| url | https://arxiv.org/abs/2601.22858 |