Expanding the dataset

In order to allow other researchers to contribute to expanding the dataset, 10 non-labelled point clouds are here available and guidelines for annotation are provided.
The dataset has been labelled with common point cloud processing software as CloudCompare. However, an in-house web annotation tool built upon the Semantic-segmentation-editor web application is also available for users at this
link

Considering each class, excluding the standard ones of walls, floors, roofs and stairs, the guidelines followed for the annotation have been:

  • Columns. In this class, only stand-alone columns or pillars have been inserted, both with circular and square sections. As mentioned above, the half-pilasters or half-columns leaning on the walls have been included in the Moldings class.

  • Moldings. Stuccos and all other types of moldings, like windows, doors or decorative moldings have been included in this class, in addition to the previously cited half-pilaster and half-columns (Figure 5). More generally, everything that protrudes from the masonry falls into this class.
  • Doors and windows have been combined into one class, given their reduced number of points and their similar geometry.

  • Vaults. Every type of vault (barrel, cross, dome …) has been included in this class. If the individual vaults were divided by protruding arches with respect to the vault itself then they were interrupted, otherwise, a unique annotation has been kept.

  • Arches. This class includes both the arches on the facade and those that divide one vault from another, but only if they are jutting.

  • Other. Everything that does not fall within the previous classes has been included here. This class has the sole purpose of maintaining some architectural or furnishing elements (downpipes, benches, balustrades …) which could be useful in the future and which, at the same time, help in the general understanding of the point cloud. For training and test phases, it is recommended to exclude this class, as it could adversely affect the loss function, the general performances of the neural networks or any other algorithms used.

For the point cloud annotation, you can choose to download one or more point clouds. The labelling consists of associating a class number to each point. Please, use the following order:

"arch":0, "column":1, "moldings":2, "floor":3, "door_window":4, "wall":5, "stairs":6, "vault":7, "roof":8, "other":9
SKIP to download

NamePhotoPreviewN. of pointsSceneSubsampling (cm)
Castiglione_street13,980,779Outdoor2
SMaggiore_street_114,990,593Outdoor1
SMaggiore_street_29,595,123Outdoor1
SMaggiore_street_317,648,318Outdoor1
SMaggiore_street_428,713,837Outdoor1
SMaggiore_street_511,973,213Outdoor1
TRE_Loggia13,011,118Outdoor/Indoor1
StLaurent_chapel43,221,134Indoor1
Dugny_church17,993,759Outdoor/Indoor1
StPierre_church57,241,903Indoor1
Novalesa_cloister22,997,759Outdoor1
TOTAL (million)251,347,536