Metraipolis › archive › dc_db1d81ed0165
ReconSplat: Generalizable 3D Scene Reconstruction Beyond Observed Views — arXiv:2608.28895
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.28895
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T09:53:25.110Z
- SHA-256 of the archived text
a13a2f478a04b384601820848f3ea3e24655d1b31c8fe754d8a85f26fc04d11f- Stable URL of this page
https://metraipolis.com/documento/dc_db1d81ed0165
How to cite
ReconSplat: Generalizable 3D Scene Reconstruction Beyond Observed Views — arXiv:2608.28895 — arXiv (en), https://arxiv.org/abs/2608.28895 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_db1d81ed0165 (Metraipolis archive dc_db1d81ed0165, sha256 a13a2f478a04b384601820848f3ea3e24655d1b31c8fe754d8a85f26fc04d11f)
BibTeX
@misc{dcdb1d81ed0165,
title = {ReconSplat: Generalizable 3D Scene Reconstruction Beyond Observed Views — arXiv:2608.28895},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.28895},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_db1d81ed0165; sha256 a13a2f478a04b384601820848f3ea3e24655d1b31c8fe754d8a85f26fc04d11f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28895. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We introduce ReconSplat, a feed-forward model for 3D scene reconstruction that aims to address the longstanding trade-off between plausible view generation for unobserved regions and geometric consistency, providing both geometrically aligned novel views and sharp depth estimates. Our approach builds on 3D Gaussian splatting (3DGS) as an intermediate differentiable scene representation and integrates it with a multi-view latent diffusion model (MV-LDM) trained to act simultaneously as a refiner and an inpainter for appearance and scene geometry. We enforce geometric consistency by guiding the diffusion process with variational 3D latent features for appearance and geometry, encoded by the feed-forward 3DGS representation and rasterized to 2D latent space. ReconSplat produces both photorealistic novel views and accurate depth maps on real-world benchmarks, RealEstate10K and DL3DV-10K, outperforming existing methods in challenging extrapolation setups. Notably, ReconSplat allows the extrapolation of unseen and challenging viewpoints jointly with coherent and precise scene geometry. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.28895 — 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 2026-10-17T09:28:47.963Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).