VertexRegen: Mesh Generation with Continuous Level of Detail
henryhj
Abstract
VertexRegen generates meshes with continuous detail by reversing edge collapse through a generative model, offering anytime generation and flexibility in detail levels.
We introduce VertexRegen, a novel mesh generation framework that enables generation at a continuous level of detail. Existing autoregressive methods generate meshes in a partial-to-complete manner and thus intermediate steps of generation represent incomplete structures. VertexRegen takes inspiration from progressive meshes and reformulates the process as the reversal of edge collapse, i.e. vertex split, learned through a generative model. Experimental results demonstrate that VertexRegen produces meshes of comparable quality to state-of-the-art methods while uniquely offering anytime generation with the flexibility to halt at any step to yield valid meshes with varying levels of detail.
Community
VertexRegen is a novel mesh generation framework that enables generation at a continuous level of detail.
Key Features:
- Progressive Mesh Formulation. VertexRegen builds on the Progressive Mesh representation (Hoppe, 1996) by learning the vertex split, i.e. reversing the edge collapse operation, as a generative problem. This foundation allows VertexRegen to inherit the benefits of progressive meshes, notably their continuous level of detail.
- Anytime Mesh Generation. Unlike existing autoregressive methods that generate meshes in a partial-to-complete manner, resulting in incomplete intermediate structures, VertexRegen generates meshes in a coarse-to-fine fashion. This means the generation process can be halted at any step to yield a valid, coarser mesh rather than an incomplete one.
Find more details, and visualisations on our project page: https://vertexregen.github.io/
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
- Mesh Silksong: Auto-Regressive Mesh Generation as Weaving Silk (2025)
- Auto-Regressive Surface Cutting (2025)
- MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Mesh (2025)
- XSpecMesh: Quality-Preserving Auto-Regressive Mesh Generation Acceleration via Multi-Head Speculative Decoding (2025)
- MeshMamba: State Space Models for Articulated 3D Mesh Generation and Reconstruction (2025)
- TextMesh4D: High-Quality Text-to-4D Mesh Generation (2025)
- 3D Shape Generation: A Survey (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
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