Multi-tiling Neural Radiance Field (NeRF) -- Geometric Assessment on Large-scale Aerial Datasets
Ningli Xu, Rongjun Qin, Debao Huang, Fabio Remondino

TL;DR
This paper presents a scalable multi-tiling NeRF method with a novel tiling strategy for large-scale aerial datasets, improving memory efficiency and geometric detail over traditional photogrammetric pipelines.
Contribution
It introduces a multi-camera tiling strategy and location-specific sampling to enhance NeRF scalability and geometric assessment on large aerial datasets.
Findings
Improved memory efficiency and convergence rate.
Better geometric completeness and detail than traditional methods.
Still lags behind in geometric accuracy.
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Vision and Imaging · Robotics and Sensor-Based Localization · Optical measurement and interference techniques
