Search academic texts

Information × Registration Number 2120U007867, Article popup.category Препринт Title Face-reenactment: generation flexibility and identity preservation (AI translated) popup.author Petruk MarianPetruk Marian popup.publication 01-01-2020 popup.source_user Український католицький університет popup.source https://hdl.handle.net/20.500.14570/4494 popup.publisher Description Face-reenactment, also knows as puppetry, has become very popular in recent years. The proposed task requires generating new face expression while preserv- ing person identity and scene features. In this work, we propose advancements for recent novel methods of accurate face-reenactment synthesis. We present results us- ing a flexible generation module, and compare different families of encoding back- bones, introduce identity loss to preserve a person’s identity in image generation with state-of-the-art models in the deep face-recognition domain. We also provide improvements in the training procedure and test on approach weaknesses. popup.nrat_date 2025-11-05 Close