Yunseok Kang  Jaeseok Lee  Jaewoong Choi  Jaekoo Lee

10.5626/JOK.2025.52.7.587

large-scale scenes 3D scene reconstruction 3D Vision 3D gaussian splatting

We proposed a strategy to mitigate the VRAM(Video Random Access Memory) shortage problem encountered when applying 3D Gaussian Splatting in large-scale 3D mapping environments derived from drone footage. To efficiently manage large scale scenes, we partitioned input data, optimized each partition independently, and subsequently merged optimized scenes. Additionally, we introduced a technique to augment point data by considering specific characteristics of drone-captured footage during the optimization process. As a result, our method reduced VRAM usage by two-thirds compared to previous studies, while achieving a 2.5% average improvement in quality as measured by PSNR(Peak Signal-to-Noise Ratio). Our approach emphasizes enhancing the accuracy and quality of 3D reconstructions while minimizing VRAM consumption.