Forum

Author Topic: Mask from model what if model cant be created as mask is needed for its making ?  (Read 1939 times)

Steve003

  • Full Member
  • ***
  • Posts: 169
    • View Profile
Hi,
 I foresee a catch22 situation.
I love the idea of saving days of masking on a 500 photo project by having agisoft be told what is the model and exclude everything else.
What if its confused with the background featuring humans, or sunlit areas with sun going in and out, or sunlit areas moving (as the sun does) during the shoot., or foliage moving etc. real world situations in fact.
Its unable to make the model which could then have all the unwanted bits removed indicating to metashape what is the model and what to mask.

Can this be so ? a catch 22 situation.

How is this situation dealt with ?

Can a mask be made in photoshop or with the mask tools and that get used to make masks for all images ? Masking every image by hand is impractical if its a complex shape such as a farm plough in a sunlit junk yard.

Steve

Alexey Pasumansky

  • Agisoft Technical Support
  • Hero Member
  • *****
  • Posts: 14813
    • View Profile
Hello Steve,

Masking from model can be helpful in the following cases:


1. In projects, where the object is scanned in several sessions, for example: top and bottom separately, after rotating the object itself. Then each sub-set of images can be processed individually in separate chunks up to the model (for example, in Medium quality), then everything not related to the object of interest (including the background, on which the object is standing) should be removed from the mesh in each chunk and the masks from the model are generated in each chunk. After that the chunks are merged (not caring about relative orientation, as it's only needed to bring the images and masks to the single chunk) and the processing is started from scratch for the complete dataset with the masks applied.

2. For projects, where some features are detected in the background or around the model, which are present even after mesh reconstruction. The mesh model for such project can be manually cleaned up (or with the help of Gradual Selection -> Connected Components filter), masks are generated from the clean model and the processing is re-started either from the very beginning or from the depth maps generation stage (to make them more clean and focused on the object of interest only).

3. Also this approach can be used even in common cases, when after building the mesh model and getting the acceptable quality you would like to try the processing with the masks applied in order to check, if it would give a better result, when the key and tie points are detected only on the surface of the object of interest.
Best regards,
Alexey Pasumansky,
Agisoft LLC

Steve003

  • Full Member
  • ***
  • Posts: 169
    • View Profile
I wish someone did a video showing all this !

Could there be a case where the model doesnt get created due to a need for masking off data in the background such as sun on items, or shadows, or humans moving about etc. What then, is that then when we need to manually mask each photo, or what is the solution ?

If the model gets created then we can delete bits off to refine it and then run mask from model to better it., as you say in para 3.

if its got some crazy lump sticking out and we remove that and can see inside where the lump had been attached, is that ok to do ? If we then go mesh use mask from model will that work with a model and a hole in it ?

Understood on 1, useful as I often have items I have to turn upside down, our Method D sheet features such and I shall make sure 1. is mentioned.

I am after creating a good step by step, that brings together all these things for a relaxing follow the steps method approach to using metashape.

At the moment one is having to pull together methods and sub methods to form the entire workflow.

Maybe a variety of objects and scenarios where each and every step is featured, video capture of the screen with someone doing it is easy to do.

Steve