Inner Space Preserving Generative Pose Machine
Shuangjun Liu, Sarah Ostadabbas

TL;DR
This paper introduces ISP-GPM, a novel generative model that reposes articulated figures in images while preserving the background, using an interpretable low-dimensional pose descriptor within a multi-stage GAN framework.
Contribution
The paper proposes a new model that effectively reposes articulated figures in images with background preservation, extending pose manipulation to more complex, real-world scenarios.
Findings
Achieved over 80% accuracy on PCK0.5 pose estimation metric.
Successfully preserved background details during reposing.
Effectively handled highly articulated human figures with diverse poses.
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsGenerative Adversarial Networks and Image Synthesis · Advanced Vision and Imaging · Computer Graphics and Visualization Techniques
MethodsConvolution · Dogecoin Customer Service Number +1-833-534-1729
