Questions about 3D Bbox

[Jiankai-Sun]

Hi, Stanford team,

Firstly, thank you for providing such a great dataset (http://buildingparser.stanford.edu/dataset.html)!

We are confused about the provided Bbox coordinates of object stored in the 'Area_#/3d/pointcloud.mat' file.

In each object struct (Area --> Disjoint-Space --> object):

• object: --> name: the name of the object, wiith per space indexing* (e.g. chair-1, wall_3, clutter_13, etc.) --> points: the X,Y,Z coordinates of the 3D points that comprise this object --> RGB_color: the raw RGB color value [0,255] associated with each point. --> global_name: the name of the object, with per area global index** --> Bbox: [Xmin Xmax Ymin Ymax Zmin Zmax] of the object's boudning box --> Voxels: [Xmin Xmax Ymin Ymax Zmin Zmax] for each voxel in a 6x6x6 grid --> Voxel_Occupancy: binary occupancy per voxel (0: empty, 1: contains points) --> Points_per_Voxel: the object points that correspond to each voxel (in XYZ coordinates)

As described, [Xmin Xmax Ymin Ymax Zmin Zmax] is the object's bounding box. However, why are the coordinates of different objects are so similar as the attached screenshot shows. It seems like there are something wrong. Is there any other operations we need to do to get the correct 3D Bbox groundtruth? Could you please provide a specific README/Instructions to guide users correctly utilize the coordinates of 3D bounding box, both in world coordinate system and camera coordinate system?

Thank you for your reply!

[ir0]

Hi Jiankai,

From the screenshot you attached in the email you sent to us (attaching below for reference), I see that there is no problem with the values (in meters), however there seems to be an issue with the order of the variables. The variables should read: [Xmin Ymin Zmin Xmax Ymax Zmax]. Thanks for letting us know, we'll update the documentation. Let us know if this didn't work for you.

Best, Iro

[Jiankai-Sun]

Thank you for your quick reply!