Understanding the Extrinsic Parameters of Human3.6M

[wenwu35]

Hi, I am trying to make sense of the extrinsic parameters of the Human3.6M dataset. I first thought the extrinsics (R, t) of each of the 4 cameras pointed to one single world coordinate center, but it didn't seem to be right after I reconstructed the cameras views using Human3.6M's extrinsic parameters (image below) - the cameras were not placed at the 4 corners of the capture space as described by Lab Setup.

Just wondering if anyone knows how each camera of Human3.6M set their O points, and are they the same point in the real physical world? Many thanks!

[una-dinosauria]

That sounds like an excellent question for the authors of the Human 3.6M dataset.