Empirical study shows stitching artifacts in patched cycleGAN volumes evade FID detection yet degrade segmentation performance, with 3D models offering limited benefit over more stable 2D training.
CycleGAN Face-off
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
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.
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Stitching and dimensionality effects on large artificially generated volume datasets
Empirical study shows stitching artifacts in patched cycleGAN volumes evade FID detection yet degrade segmentation performance, with 3D models offering limited benefit over more stable 2D training.