search

z-x-yang / CFBI

The official implementation of CFBI(+): Collaborative Video Object Segmentation by (Multi-scale) Foreground-Background Integration.
BSD 3-Clause "New" or "Revised" License
322 stars 43 forks source link

different and weird result #24

Closed luoww1992 closed 3 years ago

luoww1992 commented 3 years ago

i run the code with the bigs folder in dataset, while i test it with default dataset, result is good, like this : good

but when i change the mask in first mask image, it shows me some weird result, like this, bad

left in photo is the first key frame.

z-x-yang commented 3 years ago

Your changed mask looks good. But the number of predicted objects is not consistent with the given mask. I suppose the format of the given mask is RGB, which is not correct. Please set the format to greyscale. More details can be found in this issue.

luoww1992 commented 3 years ago

i will try to test it, thanks !