What type of study is this?

September 10, 2025The international archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciencesOpen Access

3D Façade Element Extraction from Image-based Instance Segmentation and Scale-Invariant Object Contour Points

View Full Paper

Ask AI

Bookmark

Authors

FFFlorian FrankZF Friedrichshafen (Germany)VSVeeraj ShahHospital for Special Surgery SWSimon WorbisMunich University of Applied Sciences

Discussion

Member takes

Implication

Proposed method extracts 3D façade elements using instance segmentation and scale-invariant contour points, indicating enhanced modeling capabilities.

Key Points

The method generates a photogrammetrically-derived point cloud from 6DoF poses, aiding 3D reconstruction efforts.
Key elements of LoD3 façade modeling utilize RGB images and 6DoF camera information to enhance automation.
Instance segmentation with YOLOv8 and edge detection algorithms significantly improves the accuracy of object contour extraction.
This innovative approach supports future comparisons with other point clouds, driving advancements in architectural modeling.

Cite This Study

Frank et al. (2025) studied this question.

synapsesocial.com/papers/68c1a78854b1d3bfb60e14d3 https://doi.org/10.5194/isprs-archives-xlviii-g-2025-473-2025

View Full Paper

Ask AI

Bookmark

Implication

Proposed method extracts 3D façade elements using instance segmentation and scale-invariant contour points, indicating enhanced modeling capabilities.

3D Façade Element Extraction from Image-based Instance Segmentation and Scale-Invariant Object Contour Points

Discussion

Member takes

Implication

Key Points

Cite This Study

3D Façade Element Extraction from Image-based Instance Segmentation and Scale-Invariant Object Contour Points

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider