Metraipolis › archive › dc_7322ce848fd3

PLSR: Progressive and Localized Super-Resolution of 3D Objects via Localized Latent Voxel Diffusion — arXiv:2609.06436

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.06436
License (as archived)
CC0-1.0
Archived
2026-10-16T15:07:05.412Z
SHA-256 of the archived text
26f0624882362a8096e6d0df145a305c4bdac8fe4e20987f46ba105e2ddc5651
Stable URL of this page
https://metraipolis.com/documento/dc_7322ce848fd3

How to cite

PLSR: Progressive and Localized Super-Resolution of 3D Objects via Localized Latent Voxel Diffusion — arXiv:2609.06436 — arXiv (en), https://arxiv.org/abs/2609.06436 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7322ce848fd3 (Metraipolis archive dc_7322ce848fd3, sha256 26f0624882362a8096e6d0df145a305c4bdac8fe4e20987f46ba105e2ddc5651)
BibTeX
@misc{dc7322ce848fd3,
  title = {PLSR: Progressive and Localized Super-Resolution of 3D Objects via Localized Latent Voxel Diffusion — arXiv:2609.06436},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.06436},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7322ce848fd3; sha256 26f0624882362a8096e6d0df145a305c4bdac8fe4e20987f46ba105e2ddc5651},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.06436. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

High-resolution 3D asset generation is vital in various 3D applications. Existing state-of-the-art diffusion-based models remain constrained by fixed resolutions, limiting their ability to produce details. In this paper, we tackle the challenge of generating more detailed, higher-resolution 3D objects by introducing a 3D super-resolution (SR) framework built on existing 3D generative foundation models. To this end, we design PLSR, a progressive and localized super-resolution solution to achieve this goal effectively and memory efficiently. Technically, given a coarse geometry from a pretrained 3D generator, we decompose the global SR task into localized sub-tasks via an associative input decomposition scheme, adapt a flow-based 3D generator into a localized super-resolution model through low-cost finetuning, and unify them in an iterative patch-wise denoising pipeline for seamless high-resolution output. Experiments on challenging objects show that our approach is able to generate 3D details with new strong fine-detail fidelity while significantly reducing the computational cost, offering a new and practical solution for high-resolution 3D asset generation.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Graphics (cs.GR).
Pagina del lavoro: https://arxiv.org/abs/2609.06436 — 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 2026-10-16T14:49:57.085Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).