Metraipolis › archive › dc_d7b9fd5defba

MeshCarve: Artisan Mesh Generation with Flow Matching in Compact Latent Spaces — arXiv:2610.09723

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.09723
License (as archived)
CC0-1.0
Archived
2026-10-08T12:47:32.007Z
SHA-256 of the archived text
47ca297dfb8c2036d6d8a7628ce28cda8c1b3526b005994079a359ea0b830145
Stable URL of this page
https://metraipolis.com/documento/dc_d7b9fd5defba

How to cite

MeshCarve: Artisan Mesh Generation with Flow Matching in Compact Latent Spaces — arXiv:2610.09723 — arXiv (en), https://arxiv.org/abs/2610.09723 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d7b9fd5defba (Metraipolis archive dc_d7b9fd5defba, sha256 47ca297dfb8c2036d6d8a7628ce28cda8c1b3526b005994079a359ea0b830145)
BibTeX
@misc{dcd7b9fd5defba,
  title = {MeshCarve: Artisan Mesh Generation with Flow Matching in Compact Latent Spaces — arXiv:2610.09723},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.09723},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d7b9fd5defba; sha256 47ca297dfb8c2036d6d8a7628ce28cda8c1b3526b005994079a359ea0b830145},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09723. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.09723 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T12:18:15.402Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).