Clarification regarding mask module
testingshanu opened this issue · comments
testingshanu commented
I wanted to clarify the following:
- What type of information does stereo image add to the monorec network?
- Is it possible to train the end to end model only using monocular images ?
- Is it possible to train only the mask module only using monocular images ?
Nan Yang commented
I will try to answer your questions in the following:
- The stereo images make the depth training more accurate, are crucial for the mask module refinement, and are needed for generating the auxiliary masks.
- For the depth module, yes, for the mask module, as I mentioned above, we need the stereo images for the mask module refinement and generating auxiliary masks.
- Please refer to 2.
Thanks