Gaussian Splatting for Large-Scale Aerial Scene Reconstruction From Ultra-High-Resolution Images

Simple item page
dc.contributor.authorSun, Qiulinen_US
dc.contributor.authorLai, Weien_US
dc.contributor.authorLi, Yixianen_US
dc.contributor.authorZhang, Yancien_US
dc.contributor.editorChristie, Marcen_US
dc.contributor.editorPietroni, Nicoen_US
dc.contributor.editorWang, Yu-Shuenen_US
dc.date.accessioned2025-10-07T05:03:16Z
dc.date.available2025-10-07T05:03:16Z
dc.date.issued2025
dc.description.abstractUsing 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.en_US
dc.description.number7
dc.description.sectionheadersGaussian Splatting
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume44
dc.identifier.doi10.1111/cgf.70265
dc.identifier.issn1467-8659
dc.identifier.pages11 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.70265
dc.identifier.urihttps://diglib.eg.org/handle/10.1111/cgf70265
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectCCS Concepts: Computing methodologies → Computer graphics; Machine learning
dc.subjectComputing methodologies → Computer graphics
dc.subjectMachine learning
dc.titleGaussian Splatting for Large-Scale Aerial Scene Reconstruction From Ultra-High-Resolution Imagesen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
cgf70265.pdf
Size:
30.41 MB
Format:
Adobe Portable Document Format
Download
Collections
44-Issue 7