-
Notifications
You must be signed in to change notification settings - Fork 43
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
Warping operation formula in MVSplat paper #80
Comments
Hi, @trungphien, sorry for the late reply. They should be mathematically equivalent. The main difference is that the formula is in Homogeneous coordinates, while the implementation is in Cartesian coordinates. In particular, with reference to UniMatch Eq. (9), While in the implementation, you can see that we perform separately the rotation ( mvsplat/src/model/encoder/costvolume/depth_predictor_multiview.py Lines 39 to 44 in ef976a1
Note that the mvsplat/src/model/encoder/costvolume/depth_predictor_multiview.py Lines 103 to 105 in ef976a1
Let me know if it is unclear. Cheers. |
Hi, could you describe the warping function that you use in the paper in more detail? I noticed that the code you provided and the corresponding formula in the paper "Unifying Flow, Stereo and Depth Estimation" do not match. Thank you very much!
The text was updated successfully, but these errors were encountered: