search

andrerochow / fsrt

Official implementation of the CVPR 2024 paper "FSRT: Facial Scene Representation Transformer for Face Reenactment from Factorized Appearance, Head-pose, and Facial Expression Features"
https://andrerochow.github.io/fsrt
82 stars 5 forks source link

Which key points detection algorithm is used in the paper? #10

Open KleinXin opened 1 month ago

KleinXin commented 1 month ago

I want to use more key points. thx

andrerochow commented 1 month ago

As mentioned in our paper, we use the keypoint detector from https://github.com/AliaksandrSiarohin/first-order-model. If you want to use more keypoints, you will need to train a new model from scratch.

KleinXin commented 1 month ago

As mentioned in our paper, we use the keypoint detector from https://github.com/AliaksandrSiarohin/first-order-model. If you want to use more keypoints, you will need to train a new model from scratch.

thx！I will try and give feedback either positive or negative.