What does this research mean for the field?

Explicit representations (3D Gaussian Splatting) are currently more viable than implicit representations (Neural Radiance Fields) for interactive, city-scale manipulation of large-scale aerial scenes. Novelty: ClaimNovelty.NOVEL_FINDING. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

The survey aims to compare implicit and explicit representations for editing aerial scenes captured by UAVs, emphasizing their mechanisms and challenges.

March 12, 2026Open Access

Implicit vs. explicit a comparative survey on NeRF and 3DGS for large-scale aerial scene editing

Key Points

The survey aims to compare implicit and explicit representations for editing aerial scenes captured by UAVs, emphasizing their mechanisms and challenges.
Systematic analysis of large-scale 3D data acquisition with UAV imagery.
Comparative evaluation of NeRF and 3DGS representations.
Introduction of new taxonomies for understanding editing mechanisms.
Explicit representations (3DGS) are more viable for interactive editing.
Bottlenecks identified include handling oblique views and atmospheric conditions.
Future research directions emphasize enhancing editing capabilities for aerial scenes.

Abstract

The proliferation of Unmanned Aerial Vehicles (UAVs) has significantly advanced large-scale 3D data acquisition, paving the way for Digital Twin applications. While Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) now enable exceptional photorealism, editing these vast neural representations remains a significant challenge. This survey systematically analyzes large-scale scene editing from UAV imagery, specifically focusing on the architectural dichotomy between implicit (NeRF) and explicit (3DGS) representations. We introduce novel taxonomies to deconstruct their core mechanisms and critically evaluate why explicit representations are currently emerging as the more viable path for interactive, city-scale manipulation. Furthermore, we identify key bottlenecks—such as handling oblique views and variable atmospheric conditions—and outline future research directions.A comprehensive and regularly updated collection of the surveyed papers and resources is available at our project website: https://github.com/ruigong335-creator/A-Survey-on-Aerial-Scene-Editing .

Bookmark

View Full Paper

Bookmark

View Full Paper

Implicit vs. explicit a comparative survey on NeRF and 3DGS for large-scale aerial scene editing

Key Points

Abstract

Cite This Study