Spatial Content Alignment For Pose Transfer
This addresses the challenge of generating fine-trained person images for applications like virtual try-on or animation, representing an incremental improvement over existing methods.
The paper tackles the problem of unreliable geometric matching and content misalignment in pose transfer algorithms, proposing SCAGAN to enhance content consistency and details, resulting in superior performance in quantitative and qualitative analyses compared to state-of-the-art methods.
Due to unreliable geometric matching and content misalignment, most conventional pose transfer algorithms fail to generate fine-trained person images. In this paper, we propose a novel framework Spatial Content Alignment GAN (SCAGAN) which aims to enhance the content consistency of garment textures and the details of human characteristics. We first alleviate the spatial misalignment by transferring the edge content to the target pose in advance. Secondly, we introduce a new Content-Style DeBlk which can progressively synthesize photo-realistic person images based on the appearance features of the source image, the target pose heatmap and the prior transferred content in edge domain. We compare the proposed framework with several state-of-the-art methods to show its superiority in quantitative and qualitative analysis. Moreover, detailed ablation study results demonstrate the efficacy of our contributions. Codes are publicly available at github.com/rocketappslab/SCA-GAN.