This project is a generative adversarial network designed for image animation and motion transfer. It functions as a computer vision framework that synthesizes video sequences by applying motion patterns extracted from a driving video onto a static source image.
The model distinguishes itself by using a keypoint-based representation to decouple object appearance from temporal movement. By tracking structural deformations through learned latent coordinates, it performs motion retargeting and synthetic media production without requiring manual annotations or object-specific training data.
The system utilizes dense motion field estimation and local affine transformations to warp source image features into target poses. Through an encoder-decoder architecture and adversarial training, it generates realistic video frames that map facial expressions and head movements from a source video onto a target subject.
