Progressive Pose Attention Transfer for Person Image Generation

Zhen Zhu, Tengteng Huang, Baoguang Shi, Miao Yu, Bofei Wang +1 more
4/6/2019
cs.CV

Official code: tengteng95/Pose-Transfer (741 stars, MIT, last commit 2023-02-11).

Abstract

This paper proposes a new generative adversarial network for pose transfer, i.e., transferring the pose of a given person to a target pose. The generator of the network comprises a sequence of Pose-Attentional Transfer Blocks that each transfers certain regions it attends to, generating the person image progressively. Compared with those in previous works, our generated person images possess better appearance consistency and shape consistency with the input images, thus significantly more realistic-looking. The efficacy and efficiency of the proposed network are validated both qualitatively and quantitatively on Market-1501 and DeepFashion. Furthermore, the proposed architecture can generate training images for person re-identification, alleviating data insufficiency. Codes and models are available at: https://github.com/tengteng95/Pose-Transfer.git.

View on arXivView PDF

Code Implementations(1)

tengteng95/Pose-TransferOfficial100%
MIT

Code for the paper Progressive Pose Attention for Person Image Generation in CVPR19 (Oral).

741159Shell, PythonMar 3, 20193 years agoMIT

Similar Papers

A Review on Generative Adversarial Networks for Data Augmentation in Person Re-Identification Systems

88% match1 repo52023

Pose-Normalized Image Generation for Person Re-identification

86% match1 repo1402017

A Style-Based Generator Architecture for Generative Adversarial Networks

85% match2 repos14.4k2018

Towards Robust 3D Pose Transfer with Adversarial Learning

84% match2024

Learning Invariance from Generated Variance for Unsupervised Person Re-identification

84% match1 repo82023

TIPS: Text-Induced Pose Synthesis

84% match1 repo262022

Cite this paper

@article{zhu2019progressive,
  title  = {Progressive Pose Attention Transfer for Person Image Generation},
  author = {Zhen Zhu and Tengteng Huang and Baoguang Shi and Miao Yu and Bofei Wang and Xiang Bai},
  year   = {2019},
  eprint = {1904.03349},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1904.03349}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1904.03349.svg)](https://codeofpaper.com/paper/1904.03349)

Discussion