Metraipolis › archive › dc_836aaedecb67

GSExplorer: Interactive World Generation with a Persistent 3D Gaussian World State — arXiv:2611.01543

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.01543
License (as archived)
CC0-1.0
Archived
2026-11-03T11:06:30.500Z
SHA-256 of the archived text
0cf1a528c1ceb0f38839b1a76fac8868a49b0a5c7a61cc73e2907695aa710917
Stable URL of this page
https://metraipolis.com/documento/dc_836aaedecb67

How to cite

GSExplorer: Interactive World Generation with a Persistent 3D Gaussian World State — arXiv:2611.01543 — arXiv (en), https://arxiv.org/abs/2611.01543 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_836aaedecb67 (Metraipolis archive dc_836aaedecb67, sha256 0cf1a528c1ceb0f38839b1a76fac8868a49b0a5c7a61cc73e2907695aa710917)
BibTeX
@misc{dc836aaedecb67,
  title = {GSExplorer: Interactive World Generation with a Persistent 3D Gaussian World State — arXiv:2611.01543},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01543},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_836aaedecb67; sha256 0cf1a528c1ceb0f38839b1a76fac8868a49b0a5c7a61cc73e2907695aa710917},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01543. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Interactive world generation requires both accurate local control and stable scene consistency over long rollouts. Existing methods improve local generation through camera or geometry conditioning and extend historical context with memory mechanisms. However, long-horizon exploration remains challenging as target-view guidance becomes incomplete and inconsistencies accumulate across repeated scene updates. We present \textbf{GSExplorer}, a generation--reconstruction framework built around a persistent 3D Gaussian world state. At each step, the current 3DGS scene provides multimodal rendering conditions for a condition-driven video generator, while camera geometry is injected through a separate Relative Ray Encoding branch. Generated videos are then fed back to a SLAM-based reconstruction backend, where inconsistency filtering prevents conflicting content from corrupting the scene and cross-chunk bundle adjustment improves spatial alignment across generation steps. We further design a data-construction pipeline that reproduces realistic 3DGS degradation during scene extrapolation, yielding 293K training pairs of degraded multimodal renderings and real target videos. GSExplorer achieves the best overall performance among the compared methods on both single-step and three-step WorldScore evaluation, with strong camera control and consistency across both settings, including a Camera Control score of 99.07 in single-step extrapolation. On 481-frame leave-and-return rollouts, it also shows strong revisit consistency, demonstrating the value of maintaining a reliable 3D world state for continued exploration.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.01543 — 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 2026-11-03T10:59:46.020Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).