MeshCarve: Artisan Mesh Generation with Flow Matching in Compact Latent Spaces
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.
Key points
- 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.
- To shorten the token sequence, we propose a hierarchical sparse transformer backbone, instantiated as VertexVAE and EdgeVAE.
- 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.
Sources (1)
- [1]MeshCarve: Artisan Mesh Generation with Flow Matching in Compact Latent SpacesarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 7, 09:20 AM
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.
Prior artisan mesh generation works largely predict face tokens autoregressively, which makes inference slow.
Extractive summary: sentences quoted from the sources.