Inner Space Preserving Generative Pose Machine

08/06/2018
by   Shuangjun Liu, et al.
2

Image-based generative methods, such as generative adversarial networks (GANs) have already been able to generate realistic images with much context control, specially when they are conditioned. However, most successful frameworks share a common procedure which performs an image-to-image translation with pose of figures in the image untouched. When the objective is reposing a figure in an image while preserving the rest of the image, the state-of-the-art mainly assumes a single rigid body with simple background and limited pose shift, which can hardly be extended to the images under normal settings. In this paper, we introduce an image "inner space" preserving model that assigns an interpretable low-dimensional pose descriptor (LDPD) to an articulated figure in the image. Figure reposing is then generated by passing the LDPD and the original image through multi-stage augmented hourglass networks in a conditional GAN structure, called inner space preserving generative pose machine (ISP-GPM). We evaluated ISP-GPM on reposing human figures, which are highly articulated with versatile variations. Test of a state-of-the-art pose estimator on our reposed dataset gave an accuracy over 80 preserve the background with high accuracy while reasonably recovering the area blocked by the figure to be reposed.

READ FULL TEXT

page 2

page 3

page 10

page 11

page 12

page 14

research
01/23/2022

Generative Adversarial Network Applications in Creating a Meta-Universe

Generative Adversarial Networks (GANs) are machine learning methods that...
research
01/10/2020

Can Giraffes Become Birds? An Evaluation of Image-to-image Translation for Data Generation

There is an increasing interest in image-to-image translation with appli...
research
01/19/2021

Galaxy Image Translation with Semi-supervised Noise-reconstructed Generative Adversarial Networks

Image-to-image translation with Deep Learning neural networks, particula...
research
02/01/2021

toon2real: Translating Cartoon Images to Realistic Images

In terms of Image-to-image translation, Generative Adversarial Networks ...
research
07/12/2019

Gesture-to-Gesture Translation in the Wild via Category-Independent Conditional Maps

Recent works have shown Generative Adversarial Networks (GANs) to be par...
research
01/05/2022

Culture-to-Culture Image Translation with Generative Adversarial Networks

This article introduces the concept of image "culturization", i.e., defi...
research
09/21/2022

Animating Still Images

We present a method for imparting motion to a still 2D image. Our method...

Please sign up or login with your details

Forgot password? Click here to reset