DGPose: Disentangled Semi-supervised Deep Generative Models for Human Body Analysis

@article{Bem2018DGPoseDS,
  title={DGPose: Disentangled Semi-supervised Deep Generative Models for Human Body Analysis},
  author={Rodrigo de Bem and Arnab Ghosh and Thalaiyasingam Ajanthan and Ondrej Miksik and N. Siddharth and Philip H. S. Torr},
  journal={ArXiv},
  year={2018},
  volume={abs/1804.06364}
}
Deep generative modelling for robust human body analysis is an emerging problem with many interesting applications, since it enables analysis-by-synthesis and unsupervised learning. However, the latent space learned by such models is typically not human-interpretable, resulting in less flexible models. In this work, we adopt a structured semi-supervised variational auto-encoder approach and present a deep generative model for human body analysis where the pose and appearance are disentangled in… CONTINUE READING
6
Twitter Mentions

Citations

Publications citing this paper.

References

Publications referenced by this paper.
SHOWING 1-10 OF 51 REFERENCES

A Generative Model of People in Clothing

Christoph Lassner, Gerard Pons-Moll, Peter V. Gehler
  • 2017 IEEE International Conference on Computer Vision (ICCV)
  • 2017
VIEW 14 EXCERPTS
HIGHLY INFLUENTIAL

Pose Guided Person Image Generation

  • NIPS
  • 2017
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Auto-Encoding Variational Bayes

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Real-Time Human Pose Recognition in Parts from Single Depth Images

  • Machine Learning for Computer Vision
  • 2013
VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

FLIPDIAL: A Generative Model for Two-Way Visual Dialogue

  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2018
VIEW 1 EXCERPT

Deformable GANs for Pose-Based Human Image Generation

  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2017
VIEW 1 EXCERPT

Disentangled Person Image Generation

  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2017
VIEW 1 EXCERPT