IRIS: Industrial Room In Saclay

IRIS is a new dataset providing a dense station-based LiDAR point cloud and a CAD model reconstructed close to the points in a semi-automatic way. The scene is a large industrial room (530m²) containing objects of different shapes, colors and sizes such as pipes, valves, pumps and gauges. Due to the complex environment, this dataset is challenging for many computer vision tasks.

More details are given on the dataset page.

IRIS data

• point_cloud_stations_01 to 14.zip: the raw point cloud of the entire scene with very high density. In total 67 files, one per station acquisition, and more than 2.1 billion points.
• point_cloud_stations_info.zip: the stations information. It includes the position in the scene (translation vector), and orientation (rotation vector and angle).
• point_cloud_stations_merged_zoneA to C_density_10%.ply: subparts covering in total 30% of the whole scene. Multiple station clouds have been merged. The density is 10 times lower than in the original original cloud. The resulting clouds are still dense.
• mesh_from_cad_model.ply: the mesh extracted from the cad model. It gives a surface of the cloud with high accuracy (see dataset page for more details).

IRIS-VIS data

IRIS-VIS is a dataset specifically designed for the point visibility estimation task. iris-vis.zip contains all the data. More details are given on the IRIS-VIS paper page.

• The folder show contains:
  • an example of the visibility ground truth (see paper for the ground truth construction).
  • an example of the complex visibility areas (see paper).
  • visualizations of the corrected mesh from the CAD model on a pipe and a valve (see paper).
• ZoneA, B and C are the same scenes as in IRIS. They are used for the quantitative experiments. Each scene includes:
  • 3 viewpoints.
  • for two densities (2% and 10% of the raw point cloud):
    • the input cloud (paired with the cad model).
    • for each viewpoint: the visibility ground truth cloud and indices (computed from the cad model).
    • for each viewpoint: the cloud and indices of the complex areas (computed from the ground truth).
• ZoneA.1 and A.2 are two subscenes of the zoneA used for the qualitative visualizations. They include:
  • 1 viewpoint (the same for A.1 and A.2).
  • the same data as for the scenes A, B and C (see above), including the raw and input clouds for the visibility estimation task.
  • the visibility prediction cloud and indices for each method.
  • the visibility evaluation cloud for each method: the prediction cloud merged with the ground truth cloud and colorised according to true positive (blue), false positive (purple), false negative (orange).
  • the camera parameters used for Vis2mesh.