Page 1 of 1

mask accuracy in relation to higher face coverage e.g. 87% legacy

Posted: Sat Jun 05, 2021 10:45 pm
by swapration
  1. Is it bad for masks to cover more than the edges of a face (backgrounds, hair, .etc) for models with higher coverage - for capturing a more accurate silhouette e.g. the bridge of the nose, cheekbone protrusion, etc.? Will it just add to the training time or will it draw things outside of the face during conversion?

  2. Do higher coverage models learn beyond what the mask includes? For example, with unet masks ending just above the brow, will a coverage of 87.5% (legacy) still learn some of the forehead?

  3. Also is the coverage the same between the new faceswap (extracted faces end near the collar) and the older version (extracted faces end below the chin)? Is 87.5% still down to the chin for the new version of faceswap like it was for the older version?


Re: mask accuracy in relation to higher face coverage e.g. 87% legacy

Posted: Tue Jun 08, 2021 10:10 am
by torzdf
swapration wrote: Sat Jun 05, 2021 10:45 pm
  1. Is it bad for masks to cover more than the edges of a face (backgrounds, hair, .etc) for models with higher coverage - for capturing a more accurate silhouette e.g. the bridge of the nose, cheekbone protrusion, etc.? Will it just add to the training time or will it draw things outside of the face during conversion?

For training, I don't worry too much (I figure enough masks will be correct that it will average out over time).

For convert the mask needs to be correct, bad masks will generally lead to bad converts

swapration wrote: Sat Jun 05, 2021 10:45 pm
  1. Do higher coverage models learn beyond what the mask includes? For example, with unet masks ending just above the brow, will a coverage of 87.5% (legacy) still learn some of the forehead?

No. Only what is in the mask is learned. If you have a large coverage, but the mask only includes a small part in the middle of the image, then this is all that will be learned.

swapration wrote: Sat Jun 05, 2021 10:45 pm
  1. Also is the coverage the same between the new faceswap (extracted faces end near the collar) and the older version (extracted faces end below the chin)? Is 87.5% still down to the chin for the new version of faceswap like it was for the older version?

It is for 'legacy' centering. For different centering different coverage will be required. See here: viewtopic.php?f=27&t=146#config_global


Re: mask accuracy in relation to higher face coverage e.g. 87% legacy

Posted: Wed Jun 09, 2021 9:24 pm
by swapration

I'm guessing by 'convert the mask needs to be correct' do you mean for face A, B, or both? I'm guessing you mean face A needs to be accurate due to obstructions?


Re: mask accuracy in relation to higher face coverage e.g. 87% legacy

Posted: Thu Jun 10, 2021 9:26 am
by torzdf

I mean the masks stored in the alignments file that relate to the video you will be converting on to.