BirdNeRF: Fast Neural Reconstruction of Large-Scale Scenes From Aerial Imagery

TL;DR

BirdNeRF introduces a scalable aerial scene reconstruction method that decomposes large datasets into manageable sub-scenes, enabling faster training and rendering with high visual fidelity on a single GPU.

Contribution

We propose a novel spatial decomposition and view re-rendering strategy for large-scale aerial scene reconstruction using NeRF, significantly improving speed and quality.

Findings

Reconstruction speed improved by 10x over classical photogrammetry.

Reconstruction speed improved by 50x over existing large-scale NeRF methods.

Achieved high-quality rendering on a single GPU.

Abstract

In this study, we introduce BirdNeRF, an adaptation of Neural Radiance Fields (NeRF) designed specifically for reconstructing large-scale scenes using aerial imagery. Unlike previous research focused on small-scale and object-centric NeRF reconstruction, our approach addresses multiple challenges, including (1) Addressing the issue of slow training and rendering associated with large models. (2) Meeting the computational demands necessitated by modeling a substantial number of images, requiring extensive resources such as high-performance GPUs. (3) Overcoming significant artifacts and low visual fidelity commonly observed in large-scale reconstruction tasks due to limited model capacity. Specifically, we present a novel bird-view pose-based spatial decomposition algorithm that decomposes a large aerial image set into multiple small sets with appropriately sized overlaps, allowing us to train individual NeRFs of sub-scene. This decomposition approach not only decouples rendering time from the scene size but also enables rendering to scale seamlessly to arbitrarily large environments. Moreover, it allows for per-block updates of the environment, enhancing the flexibility and adaptability of the reconstruction process. Additionally, we propose a projection-guided novel view re-rendering strategy, which aids in effectively utilizing the independently trained sub-scenes to generate superior rendering results. We evaluate our approach on existing datasets as well as against our own drone footage, improving reconstruction speed by 10x over classical photogrammetry software and 50x over state-of-the-art large-scale NeRF solution, on a single GPU with similar rendering quality.