Region-adaptive Texture Enhancement for Detailed Person Image Synthesis

TL;DR

This paper introduces RATE-Net, a novel framework that enhances detailed textures in synthesized person images by extracting residual textures and using an alternate updating strategy for improved realism.

Contribution

The paper proposes a texture enhancement module and an alternate updating strategy to improve fine-grained texture details in person image synthesis.

Findings

Outperforms existing methods on DeepFashion dataset

Produces sharper and more detailed textures in synthesized images

Maintains better shape and appearance consistency

Abstract

The ability to produce convincing textural details is essential for the fidelity of synthesized person images. However, existing methods typically follow a ``warping-based'' strategy that propagates appearance features through the same pathway used for pose transfer. However, most fine-grained features would be lost due to down-sampling, leading to over-smoothed clothes and missing details in the output images. In this paper we presents RATE-Net, a novel framework for synthesizing person images with sharp texture details. The proposed framework leverages an additional texture enhancing module to extract appearance information from the source image and estimate a fine-grained residual texture map, which helps to refine the coarse estimation from the pose transfer module. In addition, we design an effective alternate updating strategy to promote mutual guidance between two modules for better shape and appearance consistency. Experiments conducted on DeepFashion benchmark dataset have demonstrated the superiority of our framework compared with existing networks.