context-encoder icon indicating copy to clipboard operation
context-encoder copied to clipboard

Input already masked images instead of generating patches

Open cryptedp opened this issue 8 years ago • 5 comments

Hi Is it possible to input already masked images instead of generating masks in the image first and inpaint them ? The problem is, that the masks in my images will not all be in the same relative locations so I should inpaint different image regions but I don't want to generate masks myself on the image. If it is possible, should the masks satisfy some constraints (like pixel values )? Thx in advance

cryptedp avatar May 10 '17 09:05 cryptedp

Did you find the solution to the above problem ? @cryptedp

maryam089 avatar Oct 06 '17 20:10 maryam089

Yes, you can always modify the input code to do that. I only provided automatic masks for the convenience of code release and to avoid having to release masks file.

pathak22 avatar Oct 20 '17 22:10 pathak22

Did you find the way to do that @cryptedp ? It will help me a lot :)

niloleart avatar Jan 16 '18 15:01 niloleart

Yes, it was quite a hack actually. We detected the objects and modified the image, such that the object is in the middle and then we called inpaint_center to inpaint that region. Next we took the inpainted region back to its original position. It did not work that bad, however if we had multiple object instances it was quite messy and sometime the inpainting result was not that good @niloleart @maryam089

cryptedp avatar Jan 16 '18 15:01 cryptedp

Can you provide me more info about it? Or the code? :D Thanks, @cryptedp

niloleart avatar Jan 22 '18 16:01 niloleart