Multi-tiling Neural Radiance Field (NeRF) -- Geometric Assessment on Large-scale Aerial Datasets
This work addresses scalability and geometry assessment for aerial photogrammetry, but it is incremental as it builds on existing NeRF methods with specific optimizations.
The paper tackled scaling Neural Radiance Fields (NeRF) for large-scale aerial datasets by introducing a multi-camera tiling strategy to reduce memory usage and improve convergence, resulting in better completeness and object details compared to traditional photogrammetric methods, though with lower accuracy.
Neural Radiance Fields (NeRF) offer the potential to benefit 3D reconstruction tasks, including aerial photogrammetry. However, the scalability and accuracy of the inferred geometry are not well-documented for large-scale aerial assets,since such datasets usually result in very high memory consumption and slow convergence.. In this paper, we aim to scale the NeRF on large-scael aerial datasets and provide a thorough geometry assessment of NeRF. Specifically, we introduce a location-specific sampling technique as well as a multi-camera tiling (MCT) strategy to reduce memory consumption during image loading for RAM, representation training for GPU memory, and increase the convergence rate within tiles. MCT decomposes a large-frame image into multiple tiled images with different camera models, allowing these small-frame images to be fed into the training process as needed for specific locations without a loss of accuracy. We implement our method on a representative approach, Mip-NeRF, and compare its geometry performance with threephotgrammetric MVS pipelines on two typical aerial datasets against LiDAR reference data. Both qualitative and quantitative results suggest that the proposed NeRF approach produces better completeness and object details than traditional approaches, although as of now, it still falls short in terms of accuracy.