GauU-Scene: A Scene Reconstruction Benchmark on Large Scale 3D Reconstruction Dataset Using Gaussian Splatting
This provides a new benchmark for researchers in 3D reconstruction, but it is incremental as it applies an existing method (Gaussian Splatting) to a new dataset.
The paper tackles the problem of large-scale 3D scene reconstruction by introducing a benchmark using Gaussian Splatting on the U-Scene dataset, which covers over 1.5 km² and includes RGB and LiDAR data, with results showing significant differences when compared to point cloud datasets.
We introduce a novel large-scale scene reconstruction benchmark using the newly developed 3D representation approach, Gaussian Splatting, on our expansive U-Scene dataset. U-Scene encompasses over one and a half square kilometres, featuring a comprehensive RGB dataset coupled with LiDAR ground truth. For data acquisition, we employed the Matrix 300 drone equipped with the high-accuracy Zenmuse L1 LiDAR, enabling precise rooftop data collection. This dataset, offers a unique blend of urban and academic environments for advanced spatial analysis convers more than 1.5 km$^2$. Our evaluation of U-Scene with Gaussian Splatting includes a detailed analysis across various novel viewpoints. We also juxtapose these results with those derived from our accurate point cloud dataset, highlighting significant differences that underscore the importance of combine multi-modal information