lizhe00/AnimatableGaussians

Details about evaluation

initialneil opened this issue · 4 comments

initialneil commented

Great work on the new relightable extension.
As claimed in the paper, that Cam127 was used for the evaluation in Table IV.

The numerical results are computed on the 48-548 frames and the “Cam127” camera view in the “Actor01/Sequence1” from ActorsHQ dataset.

Questions are:

  1. Was the Cam127 used for training?
  2. Was the training conducted on the whole sequence (including 48-548)?
  3. Was the setting the same as the avatar.yaml files in this repo? e.g. the used_cam_ids
Jun-Pu commented

We follow the setting from https://github.com/lizhe00/AnimatableGaussians/blob/master/configs/actor01/avatar.yaml

Hi, I am also curious about the details of this quantitative comparison;

I noticed that the Actors-HQ provides three scales of each of their sequence, i.e., 1x, 2x and 4x.

So could you please tell me the ground truth resolution you used to conduct this comparison?

Thanks in advance!

lizhe00 commented

We follow the setting from https://github.com/lizhe00/AnimatableGaussians/blob/master/configs/actor01/avatar.yaml

Hi, I am also curious about the details of this quantitative comparison;

I noticed that the Actors-HQ provides three scales of each of their sequence, i.e., 1x, 2x and 4x.

So could you please tell me the ground truth resolution you used to conduct this comparison?

Thanks in advance!

We utilized the 4x with a resolution of 747x1021.

  • 👍1
Jun-Pu commented

We follow the setting from https://github.com/lizhe00/AnimatableGaussians/blob/master/configs/actor01/avatar.yaml

Hi, I am also curious about the details of this quantitative comparison;
I noticed that the Actors-HQ provides three scales of each of their sequence, i.e., 1x, 2x and 4x.
So could you please tell me the ground truth resolution you used to conduct this comparison?
Thanks in advance!

We utilized the 4x with a resolution of 747x1021.

Thank you so much!