Metraipolis › archive › dc_bd056bd67384
Holi-Spatial 360: Generative Reconstruction from Sparse Panoramas for Spatial Rendering and Intelligence — arXiv:2610.19502
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.19502
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T21:56:01.165Z
- SHA-256 of the archived text
fc2ff33aa5f1c22e0ec4bcaba8959add5824756a9392f267429b95208fd845ed- Stable URL of this page
https://metraipolis.com/documento/dc_bd056bd67384
How to cite
Holi-Spatial 360: Generative Reconstruction from Sparse Panoramas for Spatial Rendering and Intelligence — arXiv:2610.19502 — arXiv (en), https://arxiv.org/abs/2610.19502 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bd056bd67384 (Metraipolis archive dc_bd056bd67384, sha256 fc2ff33aa5f1c22e0ec4bcaba8959add5824756a9392f267429b95208fd845ed)
BibTeX
@misc{dcbd056bd67384,
title = {Holi-Spatial 360: Generative Reconstruction from Sparse Panoramas for Spatial Rendering and Intelligence — arXiv:2610.19502},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.19502},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bd056bd67384; sha256 fc2ff33aa5f1c22e0ec4bcaba8959add5824756a9392f267429b95208fd845ed},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19502. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Spatial intelligence requires scalable 3D environments that are both photorealistic and semantically grounded, yet existing indoor datasets are dominated by room-scale captures and costly LiDAR acquisition. Online real-estate platforms offer abundant panoramas of diverse multi-room homes, but sparse viewpoints and texture-poor regions make reconstruction severely under-constrained. We introduce Holi-Spatial 360, a generative reconstruction and data curation framework for converting these panoramas into annotated multi-room 3D environments. Because reconstruction quality bounds subsequent generation, our Correspondence-Guided Geometric Optimization converts feed-forward reconstruction priors into reliable cross-view constraints and builds a coherent 3D Gaussian Splatting representation as 3D spatial memory. Adapted single-image and video priors then restore appearance and complete continuous trajectories while preserving observed content. The reconstructed scenes support arbitrary RGB-D rendering and an automated curation pipeline that combines end-to-end 3D grounding with VLM-based verification. Holi360 contains over 1K multi-room 3DGS scenes, more than 100K instance annotations, and 2M spatial question-answer pairs. We also introduce the Holi360 benchmark to evaluate the spatial understanding of VLMs in real-world, multi-room indoor environments. Experiments demonstrate superior reconstruction and curation quality under sparse panoramic inputs, while fine-tuning VLMs on Holi360 substantially improves spatial reasoning capabilities. 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/2610.19502 — 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 2026-10-15T21:38:29.464Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).