Metraipolis › archive › dc_3e5bfbb6632f

DrawSplat: Atlanta World-Guided Implicit Gaussian SLAM for Indoor Reconstruction — arXiv:2610.41602

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.41602
License (as archived): CC0-1.0
Archived: 2026-11-03T05:46:26.566Z
SHA-256 of the archived text: f2efd59ebbd2a79e53d8087868330af3f5a7f8eaf8e9ececffd5660773e7bb66
Stable URL of this page: https://metraipolis.com/documento/dc_3e5bfbb6632f

How to cite

DrawSplat: Atlanta World-Guided Implicit Gaussian SLAM for Indoor Reconstruction — arXiv:2610.41602 — arXiv (en), https://arxiv.org/abs/2610.41602 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3e5bfbb6632f (Metraipolis archive dc_3e5bfbb6632f, sha256 f2efd59ebbd2a79e53d8087868330af3f5a7f8eaf8e9ececffd5660773e7bb66)

BibTeX

@misc{dc3e5bfbb6632f,
  title = {DrawSplat: Atlanta World-Guided Implicit Gaussian SLAM for Indoor Reconstruction — arXiv:2610.41602},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41602},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3e5bfbb6632f; sha256 f2efd59ebbd2a79e53d8087868330af3f5a7f8eaf8e9ececffd5660773e7bb66},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41602. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

RGB-D SLAM requires accurate online tracking, high-quality rendering, and geometrically consistent reconstruction. Existing Gaussian SLAM methods mainly optimize Gaussian primitives with photometric, depth, or local frame-to-model constraints, which are often insufficient in indoor scenes with weak textures, large planar structures, noisy depth, and long trajectories. The resulting maps may suffer from pose drift, surface thickness artifacts, noisy normals, and blurred structural boundaries. We propose DrawSplat, an Atlanta World-guided implicit Gaussian SLAM framework for indoor reconstruction. DrawSplat follows a drawing-like process: explicit point-line geometry first sketches the structural layout, and implicit neural Gaussians then fill in high-fidelity appearance and continuous geometric details. It estimates camera poses, sparse geometry, and gravity direction through point-line joint tracking, infers structural planes from tracked lines using the shared-gravity component of the Atlanta World prior, and converts them into differentiable regularization terms on Gaussian centers and normals. To improve compactness and efficiency, DrawSplat further combines an anchor-based implicit neural Gaussian representation with adaptive structural sampling, which allocates Gaussian capacity to structurally informative regions. Experiments on multiple datasets show that DrawSplat achieves robust tracking, high-fidelity rendering, and strong geometric reconstruction among Gaussian-based SLAM systems, while maintaining a practical balance among quality, efficiency, and model size.

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) ; Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2610.41602 — 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 2026-11-03T05:33:32.305Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).