…To gather the simulated dataset, we captured before and after flood pairs from 2000 viewpoints with the following modalities: non-flooded RGB image, depth map, segmentation map flooded RGB image, binary mask of the flooded area, segmentation map The camera was placed about 1.5 above ground, and has a field of view of 120 degree, and the resolution of the images is 1200 x 900.
2 PAPERS • 1 BENCHMARK
…Despite its popularity, the dataset itself does not contain ground truth for semantic segmentation. However, various researchers have manually annotated parts of the dataset to fit their necessities.
3,240 PAPERS • 141 BENCHMARKS