Results 31 to 40 of about 897,519 (241)
Large-Scale 3D Terrain Reconstruction Using 3D Gaussian Splatting for Visualization and Simulation [PDF]
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information SciencesThe fusion of low-cost unmanned aerial systems (UAS) with advanced photogrammetric techniques has revolutionized 3D terrain reconstruction, enabling the automated creation of detailed models.
M. Chen +7 more
doaj +1 more source
MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images [PDF]
European Conference on Computer VisionWe introduce MVSplat, an efficient model that, given sparse multi-view images as input, predicts clean feed-forward 3D Gaussians. To accurately localize the Gaussian centers, we build a cost volume representation via plane sweeping, where the cross-view ...
Donny Y. Chen +7 more
semanticscholar +1 more source
Orthophoto generation with gaussian splatting: mitigating reflective surface artifacts in imagery from low-cost sensors [PDF]
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information SciencesOrthophotos offer a distortion-free and high-resolution depiction of architectural and mechanical elements, serving critical functions in reverse engineering, defect detection, and condition assessment.
M. Previtali +2 more
doaj +1 more source
Evaluating 3D Gaussian Splatting for Urban Scene Reconstruction [PDF]
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information SciencesAccurate, detailed and efficient 3D reconstructions of large-scale urban environments are essential for applications such as autonomous driving, urban planning and digital twin construction.
Z. Yan +4 more
doaj +1 more source
GS-IR: 3D Gaussian Splatting for Inverse Rendering [PDF]
Computer Vision and Pattern Recognition, 2023 We propose GS-IR, a novel inverse rendering approach based on 3D Gaussian Splatting (3DGS) that leverages forward mapping volume rendering to achieve photorealistic novel view synthesis and relighting results.
Zhihao Liang +4 more
semanticscholar +1 more source
Evaluating Gaussian Splatting Maps for Absolute Visual Localization of UAVs [PDF]
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information SciencesLocalization within a global reference frame is critical for the safe operation of UAVs. It is typically realized through GNSS measurements, however when signals are jammed, spoofed, occluded or reflected, this approach can lead to errors or fail.
F. R. Matzke, H.-G. Maas, A. Eltner
doaj +1 more source
DepthSplat: Connecting Gaussian Splatting and Depth [PDF]
Computer Vision and Pattern RecognitionGaussian splatting and single-view depth estimation are typically studied in isolation. In this paper, we present Depth-Splat to connect Gaussian splatting and depth estimation and study their interactions. More specifically, we first contribute a robust
Haofei Xu +6 more
semanticscholar +1 more source
EOGS++: Earth Observation Gaussian Splatting with Internal Camera Refinement and Direct Panchromatic Rendering [PDF]
ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information SciencesRecently, 3D Gaussian Splatting has been introduced as a compelling alternative to NeRF for Earth observation, offering competitive reconstruction quality with significantly reduced training times.
P. Bournez +4 more
doaj +1 more source
GS4Buildings: Prior-Guided Gaussian Splatting for 3D Building Reconstruction [PDF]
ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information SciencesRecent advances in Gaussian Splatting (GS) have demonstrated its effectiveness in photo-realistic rendering and 3D reconstruction. Among these, 2D Gaussian Splatting (2DGS) is particularly suitable for surface reconstruction due to its flattened Gaussian
Q. Zhang, O. Wysocki, B. Jutzi
doaj +1 more source
WildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic Environments [PDF]
Computer Vision and Pattern RecognitionWe present WildGS-SLAM, a robust and efficient monocular RGB SLAM system designed to handle dynamic environments by leveraging uncertainty-aware geometric mapping. Unlike traditional SLAM systems, which assume static scenes, our approach integrates depth
Jianhao Zheng +5 more
semanticscholar +1 more source