GOHAG: GANs Orchestration for Human Actions Generation
Autor: | Geun-Sik Jo, Aziz Siyaev |
---|---|
Rok vydání: | 2020 |
Předmět: |
0303 health sciences
03 medical and health sciences Computer science Human–computer interaction Orchestration (computing) Content creation Animation 010501 environmental sciences 01 natural sciences Generative adversarial network 030304 developmental biology 0105 earth and related environmental sciences |
Zdroj: | Intelligent Information and Database Systems ISBN: 9783030419639 ACIIDS (1) |
Popis: | 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. |
Databáze: | OpenAIRE |
Externí odkaz: |