Metraipolis › archive › dc_4faec16b6844

ReconPlusGen: Injecting Reconstruction Prior into Multi-view 3D Generation through Noise Inversion and Modulation — arXiv:2609.11129

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.11129
License (as archived): CC0-1.0
Archived: 2026-10-16T06:35:14.616Z
SHA-256 of the archived text: 1c4cb02fc9d248c807254f6aca16a9f271bc9c7e5495f2e469ebd04e6427e8db
Stable URL of this page: https://metraipolis.com/documento/dc_4faec16b6844

How to cite

ReconPlusGen: Injecting Reconstruction Prior into Multi-view 3D Generation through Noise Inversion and Modulation — arXiv:2609.11129 — arXiv (en), https://arxiv.org/abs/2609.11129 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4faec16b6844 (Metraipolis archive dc_4faec16b6844, sha256 1c4cb02fc9d248c807254f6aca16a9f271bc9c7e5495f2e469ebd04e6427e8db)

BibTeX

@misc{dc4faec16b6844,
  title = {ReconPlusGen: Injecting Reconstruction Prior into Multi-view 3D Generation through Noise Inversion and Modulation — arXiv:2609.11129},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.11129},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4faec16b6844; sha256 1c4cb02fc9d248c807254f6aca16a9f271bc9c7e5495f2e469ebd04e6427e8db},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11129. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Qualitative results and an illustration of our core idea. Top left: reconstruction results on benchmark images. Top right: reconstruction results on real-world images. Bottom: illustration of reconstruction-guided noise initialization and modulation. Given multiple input images, we predict a point cloud in canonical space, deterministically inject the predicted geometry into the diffusion process through noise inversion, and modulate the resulting noise to preserve the generative flexibility required to complete unobserved regions and refine visible geometry.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-11 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.11129 — 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 2026-10-16T06:06:28.754Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).