Metraipolis › archive › dc_dbaeb58dcee5

EliGSiR: Continual RGB-D Mapping with Gaussian Splatting under Bounded Compute — arXiv:2609.20348

Source

arXiv (en)

Original

https://arxiv.org/abs/2609.20348

License (as archived)

CC0-1.0

Archived

2026-10-10T05:07:55.856Z

SHA-256 of the archived text

bec555be0235444ea7932072d24bd7053d9eb93896eac6d65800d8572d2030ac

Stable URL of this page

https://metraipolis.com/documento/dc_dbaeb58dcee5

How to cite

EliGSiR: Continual RGB-D Mapping with Gaussian Splatting under Bounded Compute — arXiv:2609.20348 — arXiv (en), https://arxiv.org/abs/2609.20348 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dbaeb58dcee5 (Metraipolis archive dc_dbaeb58dcee5, sha256 bec555be0235444ea7932072d24bd7053d9eb93896eac6d65800d8572d2030ac)

@misc{dcdbaeb58dcee5,
  title = {EliGSiR: Continual RGB-D Mapping with Gaussian Splatting under Bounded Compute — arXiv:2609.20348},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.20348},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dbaeb58dcee5; sha256 bec555be0235444ea7932072d24bd7053d9eb93896eac6d65800d8572d2030ac},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.20348. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Conventional 3D Gaussian Splatting assumes a closed set of observations and long optimization schedules. Continual RGB-D mapping in contrast poses the problem that new observations arrive online, while previously reconstructed regions must be preserved. We present EliGSiR (Evidence-guided Load-adaptive Incremental Gaussian Splatting with Image Replay), a continual Gaussian mapper that controls how the available optimization budget is used as the reconstruction evolves. Map-Guided View Scheduling filters redundant incoming views and reconsiders retained views according to the current state of the map. Load-Adaptive Fidelity adjusts supervision resolution to the current mapping load instead of following a fixed resolution schedule. Targeted Geometry Growth separates depth supervision from Gaussian creation and adds geometric capacity only where repeated RGB-D observations indicate missing or misplaced structure. Together, these mechanisms adapt which views are optimized, how much image detail is used, and where the representation grows while mapping remains active. We evaluate EliGSiR on Replica, TUM RGB-D, ScanNet++, and real RGB-D sensor sequences, considering both the final reconstruction and the map available throughout acquisition. On TUM RGB-D fr3/long_office_household, EliGSiR reaches 21.52 dB with the same ground-truth mapping poses used by the controlled baselines, compared with 19.42 dB for SplaTAM. In the tracked-pose comparison, EliGSiR with live ORB-SLAM3 poses reaches 23.02 dB in 155.5 s, compared with 20.10 dB in 230.9 s for CaRtGS using its native tracker. We further evaluate reconstruction throughout acquisition and show how EliGSiR adaptive view scheduling, supervision fidelity, and geometry growth improve the use of the available mapping budget.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-18 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.20348 — 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 2026-10-10T04:26:09.603Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).