Metraipolis › archive › dc_dbb81daa5042
GenIA: Generative Reconstruction with Test-Time Input Alignment — arXiv:2610.12388
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.12388
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T06:30:57.939Z
- SHA-256 of the archived text
7bce6e8cfadbfc87f78c94d5b6730e9386a0709d605006f5a3d82a78a56871c7- Stable URL of this page
https://metraipolis.com/documento/dc_dbb81daa5042
How to cite
GenIA: Generative Reconstruction with Test-Time Input Alignment — arXiv:2610.12388 — arXiv (en), https://arxiv.org/abs/2610.12388 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dbb81daa5042 (Metraipolis archive dc_dbb81daa5042, sha256 7bce6e8cfadbfc87f78c94d5b6730e9386a0709d605006f5a3d82a78a56871c7)
BibTeX
@misc{dcdbb81daa5042,
title = {GenIA: Generative Reconstruction with Test-Time Input Alignment — arXiv:2610.12388},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.12388},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dbb81daa5042; sha256 7bce6e8cfadbfc87f78c94d5b6730e9386a0709d605006f5a3d82a78a56871c7},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.12388. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Reconstructing complete 3D object assets from monocular or sparse multi-view observations remains challenging. Generative 3D foundation models can complete object geometry beyond the observed views, but their predictions may not faithfully reproduce the observed geometry, appearance, or pose. We introduce GenIA, a framework for test-time input-aligned generation that grounds SAM3D's generative prior in geometric and photometric observations without retraining the foundation model. We improve object pose by deriving translation and scale from geometry while retaining the learned rotation prior, and align appearance through visibility-biased attention, cross-observation fusion, and differentiable rendering guidance during denoising. An optional post-denoising refinement further adapts the appearance latent, lightweight decoder adapters, and object placement to the observations. Our framework also supports externally supplied geometry; when given temporal shapes of dynamic objects, it recovers a shared, input-aligned canonical appearance and stable world-space placement. Across synthetic and real benchmarks, GenIA improves pose prediction and object reconstruction from monocular, multi-view, and dynamic inputs, outperforming recent optimization-based, per-frame image-to-3D, and video-to-4D methods. Our project page is available at this https URL . 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/2610.12388 — 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 2026-10-09T05:55:07.701Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).