MGS-SLAM: Dense RGB-D SLAM via Multi-level Gaussian Splatting

Simple item page
dc.contributor.authorWang, Xuen_US
dc.contributor.authorLiu, Yingen_US
dc.contributor.authorChen, Xiaojunen_US
dc.contributor.authorWu, Jialinen_US
dc.contributor.authorZhang, Xiaohaoen_US
dc.contributor.authorLi, Ruihuien_US
dc.contributor.editorChen, Renjieen_US
dc.contributor.editorRitschel, Tobiasen_US
dc.contributor.editorWhiting, Emilyen_US
dc.date.accessioned2024-10-13T18:03:02Z
dc.date.available2024-10-13T18:03:02Z
dc.date.issued2024
dc.description.abstractSimultaneous localization and mapping (SLAM) are key technologies for scene perception, localization, and map construction. 3D Gaussian Splatting (3DGS), as a powerful method for geometric and appearance representation, has brought higher performance to SLAM systems. However, the existing methods based on 3D Gaussian representation use the single level of 3D Gaussian for the entire scene, resulting in their inability to effectively capture the geometric shapes and texture details of all objects in the scene. In this work, we propose a monocular dense RGB-D SLAM system that integrates multi-level features, which is achieved by using different levels of Gaussians to separately reconstruct geometric shapes and texture details. Specifically, through the Fourier transform, we capture the geometric shapes (low frequency) and texture details (high frequency) of the scene in the frequency domain, serving as the initial conditions for the Gaussian distribution. Additionally, to address the issue of different rendering outcomes (such as specular reflections) for the same 3D Gaussian under different viewpoints, we have integrated local adaptation Gaussian and local optimization techniques to compensate the discrepancies introduced by the 3D Gaussian across different viewpoints. Extensive quantitative and qualitative results demonstrate that our method outperforms the state-of-the-art methods.en_US
dc.description.sectionheaders3D Reconstruction and Novel View Synthesis I
dc.description.seriesinformationPacific Graphics Conference Papers and Posters
dc.identifier.doi10.2312/pg.20241274
dc.identifier.isbn978-3-03868-250-9
dc.identifier.pages10 pages
dc.identifier.urihttps://doi.org/10.2312/pg.20241274
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/pg20241274
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies → Reconstruction; Tracking
dc.subjectComputing methodologies → Reconstruction
dc.subjectTracking
dc.titleMGS-SLAM: Dense RGB-D SLAM via Multi-level Gaussian Splattingen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
pg20241274.pdf
Size:
2.32 MB
Format:
Adobe Portable Document Format
Download
Collections
PG2024 Conference Papers and Posters