Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Indoor 3D Reconstruction of Buildings via Azure Kinect RGB-D Camera.

Sensors (Basel, Switzerland)·2022

Same author

Towards Semantic Photogrammetry: Generating Semantically Rich Point Clouds from Architectural Close-Range Photogrammetry.

Sensors (Basel, Switzerland)·2022

See all related articles

Search research articles

Related Experiment Video

Updated: Jan 17, 2026

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring

Published on: October 24, 2025

StructScan3D v1: A First RGB-D Dataset for Indoor Building Elements Segmentation and BIM Modeling.

Ishraq Rached¹, Rafika Hajji¹, Tania Landes²

¹College of Geomatic Sciences and Surveying Engineering, Institute of Agronomy and Veterinary Medicine, Rabat 6202, Morocco.

Sensors (Basel, Switzerland)

|September 19, 2025

Summary

A new dataset, StructScan3D v1, aids automated indoor building element segmentation for Building Information Modeling (BIM). It enables better deep learning models for tasks like indoor scene reconstruction and robotics.

Keywords:

BIM Kinect Azure RGB-D dataset semantic segmentation structural elements

More Related Videos

RGB and Spectral Root Imaging for Plant Phenotyping and Physiological Research: Experimental Setup and Imaging Protocols

RGB and Spectral Root Imaging for Plant Phenotyping and Physiological Research: Experimental Setup and Imaging Protocols

Published on: August 8, 2017

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

Related Experiment Videos

Last Updated: Jan 17, 2026

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring

Published on: October 24, 2025

RGB and Spectral Root Imaging for Plant Phenotyping and Physiological Research: Experimental Setup and Imaging Protocols

RGB and Spectral Root Imaging for Plant Phenotyping and Physiological Research: Experimental Setup and Imaging Protocols

Published on: August 8, 2017

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

Area of Science:

Computer Vision
Deep Learning
Building Information Modeling (BIM)

Background:

Growing need for structured datasets in BIM for semantic segmentation of indoor elements.
Existing datasets lack comprehensive annotations for architectural and structural components.

Purpose of the Study:

Introduce StructScan3D v1, the first RGB-D dataset for automated indoor building element segmentation and modeling.
Establish a benchmark for indoor RGB-D semantic segmentation.

Main Methods:

Captured 2594 annotated frames using Kinect Azure sensor in diverse indoor environments.
Focused on six key elements: walls, floors, ceilings, windows, doors, and miscellaneous objects.
Evaluated D-Former transformer-based model and compared it with Gemini and TokenFusion.

Main Results:

D-Former achieved a mean Intersection over Union (mIoU) of 67.5% for semantic segmentation.
Demonstrated strong performance despite occlusions and depth variations.
Provided a comprehensive analysis of segmentation accuracy against state-of-the-art models.

Conclusions:

StructScan3D v1 serves as a valuable resource for advancing indoor scene reconstruction, robotics, and augmented reality.
The dataset lays the foundation for future expansions and refined annotations.
Bridges the gap between deep learning segmentation and real-world BIM applications.