MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Mesh
Abstract
MeshLLM uses large language models to generate and understand text-serialized 3D meshes by decomposing them into meaningful subunits and training with local mesh assembly strategies.
We present MeshLLM, a novel framework that leverages large language models (LLMs) to understand and generate text-serialized 3D meshes. Our approach addresses key limitations in existing methods, including the limited dataset scale when catering to LLMs' token length and the loss of 3D structural information during mesh serialization. We introduce a Primitive-Mesh decomposition strategy, which divides 3D meshes into structurally meaningful subunits. This enables the creation of a large-scale dataset with 1500k+ samples, almost 50 times larger than previous methods, which aligns better with the LLM scaling law principles. Furthermore, we propose inferring face connectivity from vertices and local mesh assembly training strategies, significantly enhancing the LLMs' ability to capture mesh topology and spatial structures. Experiments show that MeshLLM outperforms the state-of-the-art LLaMA-Mesh in both mesh generation quality and shape understanding, highlighting its great potential in processing text-serialized 3D meshes.
Community
ICCV 2025
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Argus: Leveraging Multiview Images for Improved 3-D Scene Understanding With Large Language Models. (2025)
- From One to More: Contextual Part Latents for 3D Generation (2025)
- BANG: Dividing 3D Assets via Generative Exploded Dynamics (2025)
- PlanMoGPT: Flow-Enhanced Progressive Planning for Text to Motion Synthesis (2025)
- Assembler: Scalable 3D Part Assembly via Anchor Point Diffusion (2025)
- MAGE: Multimodal Alignment and Generation Enhancement via Bridging Visual and Semantic Spaces (2025)
- MeshMamba: State Space Models for Articulated 3D Mesh Generation and Reconstruction (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
What can you do? Show me
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper