Progressive and Aligned Pose Attention Transfer for Person Image Generation

TL;DR

This paper introduces a progressive GAN with attention mechanisms for pose transfer in person image generation, producing more realistic images and aiding data augmentation for re-identification tasks.

Contribution

The paper presents a novel progressive generator with attention-based transfer blocks that improve pose transfer quality and consistency in person image synthesis.

Findings

Generated images show higher realism and better shape preservation.

The method improves data augmentation for person re-identification.

Quantitative and qualitative results validate effectiveness.

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. We design a progressive generator which comprises a sequence of transfer blocks. Each block performs an intermediate transfer step by modeling the relationship between the condition and the target poses with attention mechanism. Two types of blocks are introduced, namely Pose-Attentional Transfer Block (PATB) and Aligned Pose-Attentional Transfer Bloc ~(APATB). Compared with previous works, our model generates more photorealistic person images that retain better appearance consistency and shape consistency compared with input images. We verify the efficacy of the model on the Market-1501 and DeepFashion datasets, using quantitative and qualitative measures. Furthermore, we show that our method can be used for data augmentation for the person re-identification task, alleviating the issue of data insufficiency. Code and pretrained models are available at https://github.com/tengteng95/Pose-Transfer.git.