Adversarial Synthesis of Human Pose from Text
arXiv:2005.00340
Abstract
This work focuses on synthesizing human poses from human-level text descriptions. We propose a model that is based on a conditional generative adversarial network. It is designed to generate 2D human poses conditioned on human-written text descriptions. The model is trained and evaluated using the COCO dataset, which consists of images capturing complex everyday scenes with various human poses. We show through qualitative and quantitative results that the model is capable of synthesizing plausible poses matching the given text, indicating that it is possible to generate poses that are consistent with the given semantic features, especially for actions with distinctive poses.
arXiv commentDAGM GCPR 2020
References in corpus (7)
- Generative Adversarial Text to Image Synthesis
- Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation
- Pose Guided Person Image Generation
- Learning What and Where to Draw
- CycleGAN, a Master of Steganography
- On the regularization of Wasserstein GANs
- Controllable Text-to-Image Generation