Zobraziť v EDS

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

Uložené v:
Podrobná bibliografia
Názov: Gaussian Splatting for Large‐Scale Aerial Scene Reconstruction From Ultra‐High‐Resolution Images.
Autori: Sun, Qiulin1 (AUTHOR), Lai, Wei1 (AUTHOR), Li, Yixian1 (AUTHOR), Zhang, Yanci1 (AUTHOR)
Zdroj: Computer Graphics Forum. Oct2025, Vol. 44 Issue 7, p1-11. 11p.
Predmety: *GAUSSIAN distribution, *ALGORITHMS, IMAGE reconstruction, HIGH resolution imaging, THREE-dimensional imaging, IMAGE processing
Abstrakt: 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. [ABSTRACT FROM AUTHOR]
Copyright of Computer Graphics Forum is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Databáza: Business Source Index
Popis
Abstrakt: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. [ABSTRACT FROM AUTHOR]
ISSN:01677055
DOI:10.1111/cgf.70265