Method - Optimization
94929 opened this issue · 3 comments
Hi, I would like to see how 3.4. Optimization is done in the code.
According to README, it looks like depth2depth.cpp under ./gaps/apps directory contains the code.
However, I'm not sure where E is formed in the file.
I would appreciate if you could tell me where E is formed.
Thanks in advance.
Please see CreateDepthImage function for more details.
Sorry for re-opening the issue, I might be asking a naive question.
Since I'm new to Computer Vision, I'm not sure how the global optimization process works.
Specifically, in 3.4 Optimization,
- I have the surface normal image N and occlusion boundary image B ready
- Then I'm trying to construct the objective function E
- But I'm not sure how each term E_D, E_N and E_S are constructed
Thus, I would appreciate if you could provide me a reference (or example, if possible) of such optimization process.
(I'm trying to implement the paper in PyTorch)
Hi, have you solved your question?
I want to learn this method of the global optimization so i read depth2depth.cpp, but i still have some questions.
Could you tell me your thinking?
Thanks in advance.