Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Question about the SBMNet. #10

Open
JerryLeolfl opened this issue Dec 16, 2021 · 1 comment
Open

Question about the SBMNet. #10

JerryLeolfl opened this issue Dec 16, 2021 · 1 comment

Comments

@JerryLeolfl
Copy link

JerryLeolfl commented Dec 16, 2021

Hi,
As what mentioned in the paper, the reliability map Z is computed by
image
where I think, Z is related to the difference about the interped frame in time t by V_(t->0) and V_(t->1).
However, in the code,

image
where frame2_1 is compute by the flow SBM_ * (-1), which I think is flow from 0 to 1, not time t to 1.
In
'''frame2_1, Mask2_1 = warp(frame1_, SBM_ * (-1), return_mask=True)''', frame2_1 will be a warpped frame from frame1 to frame3, not frame2.
Hope I have maken a clear statement of my question.

@JunHeum
Copy link
Owner

JunHeum commented Jan 10, 2022

Hi, @JerryLeolfl.

SBM_ is the symmetric bilateral motion vector field from t to 1.

Under the linear motion assumption, we developed the bilateral cost volume layer, which computes matching costs between two feature maps F_0 and F_1, yielding the bilateral cost volume in time t. Consequently, it makes the SBMNet estimate V_t_1.

If you want to know in detail how to estimate V_t_1 as the SBM, BMBC which is our previous method would be helpful to understand it.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants