CVDec 9, 2017

CycleGAN Face-off

arXiv:1712.03451v524 citations
Originality Synthesis-oriented
AI Analysis

This work addresses video-based facial expression transfer for entertainment or communication applications, but it is incremental as it builds on existing CycleGAN methods.

The paper tackled the problem of unsupervised face-off style transfer by improving CycleGAN to capture facial expressions and head poses, resulting in higher consistency and stability in generated videos.

Face-off is an interesting case of style transfer where the facial expressions and attributes of one person could be fully transformed to another face. We are interested in the unsupervised training process which only requires two sequences of unaligned video frames from each person and learns what shared attributes to extract automatically. In this project, we explored various improvements for adversarial training (i.e. CycleGAN[Zhu et al., 2017]) to capture details in facial expressions and head poses and thus generate transformation videos of higher consistency and stability.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes