GRCVLGAug 12, 2025

VertexRegen: Mesh Generation with Continuous Level of Detail

arXiv:2508.09062v17 citationsh-index: 7
Originality Highly original
AI Analysis

This addresses the limitation of existing autoregressive mesh generation methods that produce incomplete structures at intermediate steps, offering more flexible mesh generation for applications like computer graphics and 3D modeling.

The paper tackles the problem of generating meshes with continuous level of detail by introducing VertexRegen, which reformulates mesh generation as the reversal of edge collapse through a generative model. The result is that VertexRegen produces meshes of comparable quality to state-of-the-art methods while enabling anytime generation with valid meshes at varying 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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes