search

DIYer22 / bpycv

Computer vision utils for Blender (generate instance annoatation, depth and 6D pose by one line code)
MIT License
470 stars 58 forks source link

Segmentation with transparent background #47

Open molnarszilard opened 1 year ago

molnarszilard commented 1 year ago

Hi, I am trying to do a semantic segmentation for a dataset containing plants. My models contain a lot of leaves, which are basically built using support squares, with an image of a leaf on them. In these images the background is transparent. In the RGB render, the leaves appear normal, the transparency works - I can only see the leaves, not their supports. However, in the depth and semantic windows, the leaves appear square (I tried .obj and .fbx formats). Is there a setting that I can use, so that, the semantic mask is created using only the visible parts, without their transparent support square? Or do I have to fix the plant models first? (In Nvidia Omniverse the segmentation is correct for these models.)

Thanks. 0

DIYer22 commented 1 year ago

Sorry, bpycv's instance mask currently does not support transparency. If you still continue to use bpycv, please consider fixing the plant models.

beyse commented 1 year ago

@DIYer22 what needs to be done to support transparency?

@molnarszilard did you found a solution or work around?

zsy950116 commented 1 year ago

您好，您的邮件我已经接收。

beyse commented 1 year ago

好的，酷

molnarszilard commented 1 year ago

No, unfortunately, I did not find a solution (although I did not have much time to deal with this problem). Maybe a clue could be a different Blender version (not with bpycv, but just in the bare Blender these squares behave differently depending on the different Blender versions - but at this moment I do not remember exactly the version number)