Tile and Slide : A New Framework for Scaling NeRF from Local to Global 3D Earth Observation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912512746717184 |
|---|---|
| author | Billouard, Camille Derksen, Dawa Constantin, Alexandre Vallet, Bruno |
| author_facet | Billouard, Camille Derksen, Dawa Constantin, Alexandre Vallet, Bruno |
| contents | Neural Radiance Fields (NeRF) have recently emerged as a paradigm for 3D reconstruction from multiview satellite imagery. However, state-of-the-art NeRF methods are typically constrained to small scenes due to the memory footprint during training, which we study in this paper. Previous work on large-scale NeRFs palliate this by dividing the scene into NeRFs. This paper introduces Snake-NeRF, a framework that scales to large scenes. Our out-of-core method eliminates the need to load all images and networks simultaneously, and operates on a single device. We achieve this by dividing the region of interest into NeRFs that 3D tile without overlap. Importantly, we crop the images with overlap to ensure each NeRFs is trained with all the necessary pixels. We introduce a novel $2\times 2$ 3D tile progression strategy and segmented sampler, which together prevent 3D reconstruction errors along the tile edges. Our experiments conclude that large satellite images can effectively be processed with linear time complexity, on a single GPU, and without compromise in quality. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_01631 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Tile and Slide : A New Framework for Scaling NeRF from Local to Global 3D Earth Observation Billouard, Camille Derksen, Dawa Constantin, Alexandre Vallet, Bruno Computer Vision and Pattern Recognition Artificial Intelligence Graphics Machine Learning Neural Radiance Fields (NeRF) have recently emerged as a paradigm for 3D reconstruction from multiview satellite imagery. However, state-of-the-art NeRF methods are typically constrained to small scenes due to the memory footprint during training, which we study in this paper. Previous work on large-scale NeRFs palliate this by dividing the scene into NeRFs. This paper introduces Snake-NeRF, a framework that scales to large scenes. Our out-of-core method eliminates the need to load all images and networks simultaneously, and operates on a single device. We achieve this by dividing the region of interest into NeRFs that 3D tile without overlap. Importantly, we crop the images with overlap to ensure each NeRFs is trained with all the necessary pixels. We introduce a novel $2\times 2$ 3D tile progression strategy and segmented sampler, which together prevent 3D reconstruction errors along the tile edges. Our experiments conclude that large satellite images can effectively be processed with linear time complexity, on a single GPU, and without compromise in quality. |
| title | Tile and Slide : A New Framework for Scaling NeRF from Local to Global 3D Earth Observation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Graphics Machine Learning |
| url | https://arxiv.org/abs/2507.01631 |