MeshCarve: Artisan Mesh Generation with Flow Matching in Compact Latent Spaces

2026-10-07

AI Summary

This study addresses the inefficiency of autoregressive 3D mesh generation and the compression quality degradation caused by joint VAE encoding. To this end, we propose MeshCarve, a framework that introduces the first full-stage spatially compressed latent generation paradigm. By decoupling vertices from edge connectivity, MeshCarve employs separate VertexVAE and EdgeVAE modules for spatial-aware compression. Furthermore, it integrates a hierarchical sparse Transformer with vertex-link encoding to achieve efficient generation via flow matching within a compact latent space. Experimental results demonstrate that MeshCarve substantially reduces token sequence length while outperforming existing state-of-the-art methods on benchmarks such as Objaverse, exhibiting strong generalization capabilities across diverse datasets.

Abstract

Prior artisan mesh generation works largely predict face tokens autoregressively, which makes inference slow. Recent methods instead flow match continuous latents built by Variational AutoEncoders (VAEs), but reconstruction quality drops significantly when geometry and topology are jointly encoded, and further when the latent space is compressed. We present MeshCarve, a flow matching method that generates entirely in compact latent spaces, generating vertex positions and edge connections separately and sidestepping the difficulty of a joint compact latent. To shorten the token sequence, we propose a hierarchical sparse transformer backbone, instantiated as VertexVAE and EdgeVAE. Instead of encoding fields over the surface voxels, both VAEs anchor on discrete vertices in their latent spaces, which drastically reduces the token sequence length, and our spatial-aware compression shortens it further without costing reconstruction. VertexVAE directly encodes vertex occupancy. For connectivity, we propose vertex-link encoding, which turns arbitrary connectivity between vertices into fixed-length continuous per-vertex embeddings and recovers complex artistic topology faithfully. MeshCarve combines these VAEs with an anchor generator and flow matches on the shortened token sequences. It shows advantages over state-of-the-art autoregressive and flow matching methods on Objaverse and generalizes to Toys4K. To the best of our knowledge, it is among the first artisan mesh generation methods whose every generative stage runs in a spatially compressed latent, with a token sequence only a fraction of the most compressed previous autoregressive and flow matching works.

Problem

• artisan mesh generation
• flow matching
• compact latent space
• reconstruction quality
• inference speed

Innovation

• Flow Matching
• Compact Latent Space
• Artisan Mesh Generation
• Hierarchical Sparse Transformer
• Vertex-Link Encoding