QuadGPT: Native Quadrilateral Mesh Generation with Autoregressive Models
This work addresses a bottleneck in professional 3D content creation by providing a more efficient and higher-quality method for generating structured 3D assets.
QuadGPT tackles the problem of generating quadrilateral-dominant meshes by introducing an autoregressive framework that directly produces quad meshes end-to-end, significantly surpassing previous triangle-to-quad conversion methods in geometric accuracy and topological quality.
The generation of quadrilateral-dominant meshes is a cornerstone of professional 3D content creation. However, existing generative models generate quad meshes by first generating triangle meshes and then merging triangles into quadrilaterals with some specific rules, which typically produces quad meshes with poor topology. In this paper, we introduce QuadGPT, the first autoregressive framework for generating quadrilateral meshes in an end-to-end manner. QuadGPT formulates this as a sequence prediction paradigm, distinguished by two key innovations: a unified tokenization method to handle mixed topologies of triangles and quadrilaterals, and a specialized Reinforcement Learning fine-tuning method tDPO for better generation quality. Extensive experiments demonstrate that QuadGPT significantly surpasses previous triangle-to-quad conversion pipelines in both geometric accuracy and topological quality. Our work establishes a new benchmark for native quad-mesh generation and showcases the power of combining large-scale autoregressive models with topology-aware RL refinement for creating structured 3D assets.