A conditional deep generative model of people in natural images
We propose a deep generative model of humans in natural images which keeps 2D pose separated from other latent factors of variation, such as background scene and clothing. In contrast to methods that learn generative models of low-dimensional representations, e.g., segmentation masks and 2D skeleton...
Prif Awduron: | De Bem, R, Ghosh, A, Boukhayma, A, Ajanthan, T, Siddharth, N, Torr, P |
---|---|
Fformat: | Conference item |
Cyhoeddwyd: |
IEEE
2019
|
Eitemau Tebyg
-
DGPose: Deep Generative Models for Human Body Analysis
gan: de Bem, R, et al.
Cyhoeddwyd: (2020) -
A semi-supervised deep generative model for human body analysis
gan: De Bem, R, et al.
Cyhoeddwyd: (2019) -
3D hand shape and pose from images in the wild
gan: Boukhayma, A, et al.
Cyhoeddwyd: (2020) -
Looking deep at people: towards understanding and generating humans in images with deep learning
gan: de Bem, RA
Cyhoeddwyd: (2018) -
Cross-modal deep face normals with deactivable skip connections
gan: Abrevaya, VF, et al.
Cyhoeddwyd: (2020)