Combining Attention with Flow for Person Image Synthesis

TL;DR

This paper introduces a novel person image synthesis model that combines attention and flow-based operations to improve the accuracy of target structures and realism of textures, demonstrating superior results and versatility.

Contribution

The paper proposes a new model that integrates attention with flow-based operations for enhanced person image synthesis, showing improved performance over existing methods.

Findings

Outperforms existing models in accuracy and realism

Demonstrates versatility in portrait image editing

Validated through extensive experiments and ablation studies

Abstract

Pose-guided person image synthesis aims to synthesize person images by transforming reference images into target poses. In this paper, we observe that the commonly used spatial transformation blocks have complementary advantages. We propose a novel model by combining the attention operation with the flow-based operation. Our model not only takes the advantage of the attention operation to generate accurate target structures but also uses the flow-based operation to sample realistic source textures. Both objective and subjective experiments demonstrate the superiority of our model. Meanwhile, comprehensive ablation studies verify our hypotheses and show the efficacy of the proposed modules. Besides, additional experiments on the portrait image editing task demonstrate the versatility of the proposed combination.