Metraipolis › archive › dc_62fa99b69fe6

JoVox: Joint Hierarchical Flow Matching for Lightweight Voxel Generation — arXiv:2611.10690

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.10690
License (as archived)
CC0-1.0
Archived
2026-11-10T18:47:20.528Z
SHA-256 of the archived text
11ea4c4acfb28440b64be6c8ca00adbab0c5d229a92664bf96c34f69b06c8afa
Stable URL of this page
https://metraipolis.com/documento/dc_62fa99b69fe6

How to cite

JoVox: Joint Hierarchical Flow Matching for Lightweight Voxel Generation — arXiv:2611.10690 — arXiv (en), https://arxiv.org/abs/2611.10690 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_62fa99b69fe6 (Metraipolis archive dc_62fa99b69fe6, sha256 11ea4c4acfb28440b64be6c8ca00adbab0c5d229a92664bf96c34f69b06c8afa)
BibTeX
@misc{dc62fa99b69fe6,
  title = {JoVox: Joint Hierarchical Flow Matching for Lightweight Voxel Generation — arXiv:2611.10690},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.10690},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_62fa99b69fe6; sha256 11ea4c4acfb28440b64be6c8ca00adbab0c5d229a92664bf96c34f69b06c8afa},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.10690. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Generating high-fidelity voxels while keeping their lightweight nature remains an open problem in computer vision. Current generators are either high-fidelity but computationally heavy, or lightweight but of lower fidelity. Hierarchical methods keep the lightweight nature of voxels. However, their coarse levels, which decide where all finer cells can appear, are generated with the least information about the shape and are never revisited, so they are often plausible but wrong. Our key insight is to let finer cells take part in deciding coarse cells. To this end, we propose JoVox, a discrete flow matching framework that learns the joint distribution of all levels of the voxel hierarchy, instead of a separate distribution for each level, so that coarse cells can be predicted with finer cells already generated nearby. Within this framework, we further introduce a two-level prediction, which outputs the cells two levels finer at once instead of one level finer, halving the number of levels that the network processes and yielding voxels of higher fidelity. We also introduce an unmasking strategy that revisits early decisions once finer cells are generated and corrects inconsistencies in masked diffusion models. Our framework outperforms the baselines on both unconditional and image-conditioned voxel generation. Compared with the current state-of-the-art TRELLIS.2, we achieve 8x higher training throughput, 1/15 of the FLOPs in a forward pass, train on 4 vs. 32 GPUs, and obtain higher quality with an 11% lower Chamfer distance.

Tema degli esploratori: economia dei servizi IA (elenco arXiv cs.GT, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Computer Science and Game Theory (cs.GT).
Pagina del lavoro: https://arxiv.org/abs/2611.10690 — 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 2026-11-10T18:39:07.430Z dalla pagina https://arxiv.org/list/cs.GT/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).