合成图的时候，xseg的几个模式代表的意思是啥

maoyu

星级打分

• 1
• 2
• 3
• 4
• 5

平均分:NAN  参与人数:0  我的评分:未评

求大佬们指点

Hedwig

dst : uses masks derived from the shape of the landmarks generated during data_dst faceset/dataset extraction.
learned-prd : uses masks learned during training. Keep shape of SRC faces.
learned-dst : uses masks learned during training. Keep shape of DST faces.
learned-prd*dst : combines both masks, smaller size of both.
learned-prd+dst : combines both masks, bigger size of both.
XSeg-prd : uses XSeg model to mask using data from source faces.
XSeg-dst : uses XSeg model to mask using data from destination faces.
XSeg-prd*dst : combines both masks, smaller size of both.
learned-prd*dst*XSeg-dst*prd : Learned-prd * dst * XSeg-dst * prd:combines all 4 mask modes, smaller size of all.


我理解的加号是取两个区域的合集，乘号则是取两个区域的交集

ycqhy17

感谢分享

juv3125251

谢谢分享

maoyu

Hedwig 发表于 2021-10-31 19:44
dst : uses masks derived from the shape of the landmarks generated during data_dst faceset/dataset e ...

有点意思，我试了几个，xseg-dst合成效果好点

maoyu

还是想更直白的了解下具体功能。

无敌小金鱼

maoyu 发表于 2021-11-1 00:41
还是想更直白的了解下具体功能。

一楼给出来的那段英文 你翻译一下其实就知道大概意思了。如果是用的万能遮罩或者别地方下的遮罩模型，就选带xseg字样的就行。

maoyu

无敌小金鱼 发表于 2021-11-1 03:28
一楼给出来的那段英文 你翻译一下其实就知道大概意思了。如果是用的万能遮罩或者别地方下的遮罩模型，就 ...

好的，谢谢大佬，