Drone-NeRF: Efficient NeRF based 3D scene reconstruction for large-scale drone survey.

Neural rendering has garnered substantial attention owing to its capacity for creating realistic 3D scenes. However, its applicability to extensive scenes remains challenging, with limitations in effectiveness. In this work, we propose the Drone-NeRF framework to enhance the efficient reconstruction of unbounded large-scale scenes suited for drone oblique photography using Neural Radiance Fields (NeRF). Our approach involves dividing the scene into uniform sub-blocks based on camera position and depth visibility. Sub-scenes are trained in parallel using NeRF, then merged for a complete scene. We refine the model by optimizing camera poses and guiding NeRF with a uniform sampler. Integrating chosen samples enhances accuracy. A hash-coded fusion MLP accelerates density representation, yielding RGB and Depth outputs. Our framework accounts for sub-scene constraints, reduces parallel-training noise, handles shadow occlusion, and merges sub-regions for a polished rendering result. Moreover, our framework can be enhanced through the integration of semantic scene division, ensuring consistent allocation of identical objects to the same sub-block for improved object integrity and rendering performance. This Drone-NeRF framework demonstrates promising capabilities in addressing challenges related to scene complexity, rendering efficiency, and accuracy in drone-obtained imagery. • Propose a novel neural radiance fields framework for drone view reconstruction. • Parallel sub-block training achieves fast convergence and optimization. • Merge sub-blocks for large scenes and refine bounds to reduce edge shadows. • Semantic division assigns the same entities to sub-blocks for improved rendering. [ABSTRACT FROM AUTHOR]