search

google-research / corenet

CoReNet is a technique for joint multi-object 3D reconstruction from a single RGB image.
Apache License 2.0
104 stars 14 forks source link

How to get "mesh_visible_fractions" #5

Closed njfugit closed 2 years ago

njfugit commented 2 years ago

Hi, After reading the Data formats and coordinate systems document. I want to know how the value of "mesh_visible_fractions" mentioned in "Scene fields" is obtained. thanks.

vitaminSP commented 2 years ago

Hi, mesh_visible_fractions is computed as the number of pixels in the modal mask of each object divided by the number of pixels in its amodal mask.

njfugit commented 2 years ago

Hi, mesh_visible_fractions is computed as the number of pixels in the modal mask of each object divided by the number of pixels in its amodal mask.

I have solved it, thanks