SAGS: Structure-Aware 3D Gaussian Splatting
File(s)
Accepted version
Author(s)
Ververas, Evangelos
Potamias, Rolandos Alexandros
Song, Jifei
Deng, Jiankang
Zafeiriou, Stefanos
Type
Conference Paper
Abstract
Following the advent of NeRFs, 3D Gaussian Splatting (3D-GS) has paved the way to real-time neural rendering overcoming the computational burden of volumetric methods. Several extensions of 3D-GS have been proposed to achieve compressible and high-fidelity performance. However, by employing a geometry-agnostic optimization scheme, these methods neglect the inherent 3D structure of the scene, thereby restricting the expressivity and the quality of the representation, resulting in various floating points and artifacts. In this work, we propose a structure-aware Gaussian Splatting method (SAGS) that implicitly encodes the geometry of the scene, which reflects to state-of-the-art rendering performance and reduced storage requirements on benchmark datasets. SAGS is founded on a local-global graph representation that facilitates the learning of complex scenes and enforces meaningful point displacements that preserve the scene’s geometry. Additionally, we introduce a lightweight version of SAGS, using a simple yet effective mid-point interpolation scheme, which showcases a compact representation of the scene with up to 24 x size reduction without the reliance on any compression strategies. Extensive experiments across multiple benchmark datasets demonstrate the superiority of SAGS compared to state-of-the-art 3D-GS methods under both rendering quality and model size. Besides, we demonstrate that our structure-aware method can effectively mitigate floating artifacts and irregular distortions of previous methods while obtaining precise depth maps.
Date Issued
2024-12-06
Date Acceptance
2024-09-29
Citation
Computer Vision – ECCV 2024, 2024, pp.221-238
ISBN
978-3-031-72654-5
Publisher
Springer, Cham
Start Page
221
End Page
238
Journal / Book Title
Computer Vision – ECCV 2024
Copyright Statement
Copyright © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025. This is the author’s accepted manuscript made available under a CC-BY licence in accordance with Imperial’s Research Publications Open Access policy (www.imperial.ac.uk/oa-policy)
License URL
Source
Computer Vision – ECCV 2024 18th European Conference
Subjects
Artificial Intelligence & Image Processing
Publication Status
Published
Start Date
2024-09-29
Finish Date
2024-10-04
Coverage Spatial
Milan, Italy
Date Publish Online
2024-12-06