Gaussian Building Mesh (GBM): Extract a Building's 3D Mesh with Google Earth and Gaussian Splatting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gao, Kyle, Li, Liangzhi, He, Hongjie, Lu, Dening, Xu, Linlin, Li, Jonathan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917158587465728
author Gao, Kyle
Li, Liangzhi
He, Hongjie
Lu, Dening
Xu, Linlin
Li, Jonathan
author_facet Gao, Kyle
Li, Liangzhi
He, Hongjie
Lu, Dening
Xu, Linlin
Li, Jonathan
contents Recently released open-source pre-trained foundational image segmentation and object detection models (SAM2+GroundingDINO) allow for geometrically consistent segmentation of objects of interest in multi-view 2D images. Users can use text-based or click-based prompts to segment objects of interest without requiring labeled training datasets. Gaussian Splatting allows for the learning of the 3D representation of a scene's geometry and radiance based on 2D images. Combining Google Earth Studio, SAM2+GroundingDINO, 2D Gaussian Splatting, and our improvements in mask refinement based on morphological operations and contour simplification, we created a pipeline to extract the 3D mesh of any building based on its name, address, or geographic coordinates.
format Preprint
id arxiv_https___arxiv_org_abs_2501_00625
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Gaussian Building Mesh (GBM): Extract a Building's 3D Mesh with Google Earth and Gaussian Splatting
Gao, Kyle
Li, Liangzhi
He, Hongjie
Lu, Dening
Xu, Linlin
Li, Jonathan
Computer Vision and Pattern Recognition
Graphics
Recently released open-source pre-trained foundational image segmentation and object detection models (SAM2+GroundingDINO) allow for geometrically consistent segmentation of objects of interest in multi-view 2D images. Users can use text-based or click-based prompts to segment objects of interest without requiring labeled training datasets. Gaussian Splatting allows for the learning of the 3D representation of a scene's geometry and radiance based on 2D images. Combining Google Earth Studio, SAM2+GroundingDINO, 2D Gaussian Splatting, and our improvements in mask refinement based on morphological operations and contour simplification, we created a pipeline to extract the 3D mesh of any building based on its name, address, or geographic coordinates.
title Gaussian Building Mesh (GBM): Extract a Building's 3D Mesh with Google Earth and Gaussian Splatting
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2501.00625