Region-adaptive Texture Enhancement for Detailed Person Image Synthesis
This addresses the fidelity issue in person image synthesis for applications like virtual try-on, but it is incremental as it builds on existing warping-based strategies.
The paper tackles the problem of over-smoothed and detail-missing textures in synthesized person images by proposing RATE-Net, which uses a texture enhancing module and alternate updating strategy to achieve sharper details, outperforming existing methods on the DeepFashion benchmark.
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.