Gaussian Splatting for Large-Scale Aerial Scene Reconstruction From Ultra-High-Resolution Images
Loading...
Date
2025
Authors
Sun, Qiulin
Lai, Wei
Li, Yixian
Zhang, Yanci
Lai, Wei
Li, Yixian
Zhang, Yanci
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association and John Wiley & Sons Ltd.
Abstract
Using 3D Gaussian splatting to reconstruct large-scale aerial scenes from ultra-high-resolution images is still a challenge problem because of two memory bottlenecks - excessive Gaussian primitives and the tensor sizes for ultra-high-resolution images. In this paper, we propose a task partitioning algorithm that operates in both object and image space to generate a set of small-scale subtasks. Each subtask's memory footprints is strictly limited, enabling training on a single high-end consumer-grade GPU. More specifically, Gaussian primitives are clustered into blocks in object space, and the input images are partitioned into sub-images according to the projected footprints of these blocks. This dual-space partitioning significantly reduces training memory requirements. During subtask training, we propose a depth comparison method to generate a mask map for each sub-image. This mask map isolates pixels primarily contributed by the Gaussian primitives of the current subtask, excluding all other pixels from training. Experimental results demonstrate that our method successfully achieves large-scale aerial scene reconstruction using 9K resolution images on a single RTX 4090 GPU. The novel views synthesized by our method retain significantly more details than those from current state-of-the-art methods.
Description
CCS Concepts: Computing methodologies → Computer graphics; Machine learning
@article{10.1111:cgf.70265,
journal = {Computer Graphics Forum},
title = {{Gaussian Splatting for Large-Scale Aerial Scene Reconstruction From Ultra-High-Resolution Images}},
author = {Sun, Qiulin and Lai, Wei and Li, Yixian and Zhang, Yanci},
year = {2025},
publisher = {The Eurographics Association and John Wiley & Sons Ltd.},
ISSN = {1467-8659},
DOI = {10.1111/cgf.70265}
}