Indoor Asset Detection in Large Scale 360{\deg} Drone-Captured Imagery via 3D Gaussian Splatting

TL;DR

This paper introduces a novel 3D Gaussian Splatting-based method for indoor asset detection and segmentation from drone imagery, leveraging a 3D object codebook and multi-view mask aggregation.

Contribution

It presents a new approach combining 3D Gaussian Splatting with mask semantics for improved multi-view indoor asset detection and segmentation.

Findings

Achieved a 65% F1 score improvement over baselines.

Improved object detection mAP by 11% over existing methods.

Demonstrated reliable multi-view mask consistency in large indoor scenes.

Abstract

We present an approach for object-level detection and segmentation of target indoor assets in 3D Gaussian Splatting (3DGS) scenes, reconstructed from 360{\deg} drone-captured imagery. We introduce a 3D object codebook that jointly leverages mask semantics and spatial information of their corresponding Gaussian primitives to guide multi-view mask association and indoor asset detection. By integrating 2D object detection and segmentation models with semantically and spatially constrained merging procedures, our method aggregates masks from multiple views into coherent 3D object instances. Experiments on two large indoor scenes demonstrate reliable multi-view mask consistency, improving F1 score by 65% over state-of-the-art baselines, and accurate object-level 3D indoor asset detection, achieving an 11% mAP gain over baseline methods.