-
Hi,
We have tried your code on 3D face alignment, which works fine. However, when you change the 3D coordinates to the 2D coordinates while keeping the codes and networks the same, we cannot achiev…
-
My 5 landmarks come from GT and use pre-trained model FaceReconModel.pb, but they are far from the author's performance. why?Is there any way to improve?Thank you~
![image](https://user-images.github…
-
Hi, thanks a lot for your project!
I want to use your LS3D-W dataset as my training set. But when I get access to the .t7 annotation file, I get the 68*2 array, instead of 68*3 with depth dimension…
-
Face alignment evaluation result of AFLW in the paper and my evaluation result are different.
Could you provide the evaluation code of AFLW dataset?
-
Hello!
Where can one see the delta_a's (pose+intrinsics) / delta_b`s (3D-Landmarks/structure) regarding bundle adjustment algorithm per iteration?
Which parameter is it? I want to print them or sa…
-
Hello,
I am trying to transform the 2D pixel position of my custom detected points on the 3D face surface, by using the estimated rotation and translation coming from OpenFace. Such transformation …
-
Is there a way to get a pointcloud from VI-map online?
I have `--rovioli_visualize_map` enabled, but it publishes a cloud (landmarks) just in the end of the session. I guess because initializeLandmar…
-
Hi,
I am kind of new to pytorch, did anyone know which script should I run in order to predict 2D or 3D landmarks for a given facial image? or should I write a new testing code and use the model s…
-
-
Hello,
I would like to add some constraints to Bundle Adjustment process. For example, imagine in the environment there are some landmarks that we know their relative locations (e.g. distance betwe…