GOHAG: GANs Orchestration for Human Actions Generation

초록

Generative Adversarial Networks (GANs) made a huge contribution to the development of content creation technologies. Important place in this advancement takes video generation due to the need for human animation applications, automatic trailer or movie generation. Therefore, taking advantage of various GANs, we proposed own method for human movement video generation GOHAG: GANs Orchestration for Human Actions Generations. GOHAG is an orchestra of three GANs, where Poses generation GAN (PGAN) creates a sequence of poses, Poses Optimization GAN (POGAN) optimizes them, and Frames generation GAN (FGAN) attaches texture for the sequence, creating a video. The proposed method generates a smooth and plausible video of high-quality and showed potentials among modern techniques.

키워드