scholar.google.com › citations
Oct 21, 2023 · In this work, we design a new unsupervised face animation approach to learn simultaneously the coarse and finer motions.
Unsupervised face animation aims to generate a human face video based on theappearance of a source image, mimicking the motion from a driving video.
This paper proposes a method for face animation via learning to refine a coarse motion field. The refinement is performed in a recurrent manner using the ...
Dec 1, 2023 · Codes of the NeurIPS 2023 paper "Learning Motion Refinement for Unsupervised Face Animation" will be released here in a few days.
May 30, 2024 · In this work, we design a new unsupervised face animation approach to learn simultaneously the coarse and finer motions. In particular, while ...
Article,. Learning Motion Refinement for Unsupervised Face Animation. J. Tao, S. Gu, W.
People also search for
The landmark detector can learn to detect landmarks in an unsupervised way. It assumes locally rigid motion model surrounding each landmark. First-order [41] ...
Learning Motion Refinement for Unsupervised Face Animation. J Tao, S Gu, W Li, L Duan. Advances in Neural Information Processing Systems 36, 2024. 1, 2024.
Abstract. Image animation aims to animate a source image by using motion learned from a driving video. Current state-of-the-art methods.
Through modeling the head motion and facial expressions (In our setting, facial expression means facial movement (e.g., blinks, and lip & chin movements).) ...