Metraipolis › archive › dc_63e2c8767978

VoxLution: Evolving Voxels for High-Fidelity 3D Scene Generation — arXiv:2610.41501

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.41501
License (as archived)
CC0-1.0
Archived
2026-11-03T05:46:24.683Z
SHA-256 of the archived text
bc50b7a24f0d482a8e3a6ea21ca987df2caecc8df36233f265494cfa7e9e0cda
Stable URL of this page
https://metraipolis.com/documento/dc_63e2c8767978

How to cite

VoxLution: Evolving Voxels for High-Fidelity 3D Scene Generation — arXiv:2610.41501 — arXiv (en), https://arxiv.org/abs/2610.41501 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_63e2c8767978 (Metraipolis archive dc_63e2c8767978, sha256 bc50b7a24f0d482a8e3a6ea21ca987df2caecc8df36233f265494cfa7e9e0cda)
BibTeX
@misc{dc63e2c8767978,
  title = {VoxLution: Evolving Voxels for High-Fidelity 3D Scene Generation — arXiv:2610.41501},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41501},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_63e2c8767978; sha256 bc50b7a24f0d482a8e3a6ea21ca987df2caecc8df36233f265494cfa7e9e0cda},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41501. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

High-resolution 3D indoor scene generation is crucial for immersive applications such as virtual reality, spatial computing, and robotics simulation. We introduce VoxLution, a coarse-to-fine transformer-based approach that generates high-fidelity indoor scenes with rich details, overcoming the overly smooth geometry typical of existing generative models. First, we generate a low-resolution spatial layout; then, based on this structural information, we progressively refine the scene geometry locally in chunks. Key to our approach is formulating 3D super-resolution as a sequence modeling problem over multi-resolution sparse voxel grids. To achieve this, we introduce a training-free, resolution-invariant tokenization scheme that compactly encodes the geometric information of eight octants into a single decimal number. We formulate the transformer sequence to include multiple resolutions, allowing the coarse layout to guide the generation of fine local details. To ensure coherence across local chunks, we incorporate adjacent chunk boundary information directly into the transformer sequencing. VoxLution achieves scene generation at a finer voxel resolution than existing baselines, demonstrating state-of-the-art performance on standard benchmarks with 59.6% lower FPD and 51.1% lower FID on 3D-FRONT, and 70.5% lower FPD and 73.8% lower FID on Scannet++.

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/2610.41501 — 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 2026-11-03T05:33:32.300Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).