Metraipolis › archive › dc_b8a4fc43d850
RoSe-SLAM: Robust Semantic-Aware Gaussian Splatting SLAM from Dynamic Monocular Videos — arXiv:2608.29003
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.29003
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T07:47:26.271Z
- SHA-256 of the archived text
a483d12780a6d814a4aa4e8f5cd19f462199baae10be508b0563aedeb0bb36be- Stable URL of this page
https://metraipolis.com/documento/dc_b8a4fc43d850
How to cite
RoSe-SLAM: Robust Semantic-Aware Gaussian Splatting SLAM from Dynamic Monocular Videos — arXiv:2608.29003 — arXiv (en), https://arxiv.org/abs/2608.29003 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b8a4fc43d850 (Metraipolis archive dc_b8a4fc43d850, sha256 a483d12780a6d814a4aa4e8f5cd19f462199baae10be508b0563aedeb0bb36be)
BibTeX
@misc{dcb8a4fc43d850,
title = {RoSe-SLAM: Robust Semantic-Aware Gaussian Splatting SLAM from Dynamic Monocular Videos — arXiv:2608.29003},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.29003},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b8a4fc43d850; sha256 a483d12780a6d814a4aa4e8f5cd19f462199baae10be508b0563aedeb0bb36be},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29003. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In dynamic and unstructured environments, conventional SLAM systems generally suffer from significant accuracy degeneration due to their static assumptions. In this work, we propose Robust Semantic-aware Gaussian Splatting SLAM (RoSe-SLAM), to address the dynamic challenge by a holistic semantic scene understanding from uncalibrated monocular inputs, achieving accurate camera tracking and high-quality geometry reconstruction. Unlike conventional semantic SLAM using handcrafted semantic labels, our RoSe-SLAM exploits the semantic feature from 2D foundation model to enhance the dynamic tracking and mapping performance. By distilling the rich semantic features to our Gaussian fields, our method effectively identifies dynamic distractors and achieves semantic-aware multi-view consistency, significantly enhancing the geometric reconstruction and scene inpainting. Specifically, we propose a spatial-temporal motion mask generation module, enabling both long-term motion monitoring and short-term transient dynamics capturing, achieving robust and effective disentanglement of dynamic objects and static backgrounds. During global bundle adjustment, we propose an occlusion-aware keyframe selection mechanism to prioritize the occlusion as metric to pick the keyframes, and a multi-view semantic consistency module to improve the mapping quality in dynamic environments. By combining geometric motion cues with semantic priors, our system dynamically filters unreliable observations and reconstructs accurate static scene geometry. Extensive experiments conducted on benchmark datasets including dynamic TUM, Bonn and Wild-Mocap datasets, demonstrate that our method achieves superior performance in both trajectory estimation and static scene mapping, outperforming existing dynamic RGB SLAM baselines in long-term dynamic indoor environments. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.29003 — 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 2026-10-17T07:28:26.710Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).