FDA-GAN: Flow-based Dual Attention GAN for Human Pose Transfer
This work addresses the challenge of generating realistic human images with transferred poses for applications like animation or virtual try-on, representing an incremental improvement over existing flow-based methods.
The paper tackles the problem of preserving appearance details in human pose transfer by proposing FDA-GAN, which uses a dual attention mechanism for occlusion- and deformation-aware feature fusion, resulting in outperforming state-of-the-art models on iPER and DeepFashion datasets.
Human pose transfer aims at transferring the appearance of the source person to the target pose. Existing methods utilizing flow-based warping for non-rigid human image generation have achieved great success. However, they fail to preserve the appearance details in synthesized images since the spatial correlation between the source and target is not fully exploited. To this end, we propose the Flow-based Dual Attention GAN (FDA-GAN) to apply occlusion- and deformation-aware feature fusion for higher generation quality. Specifically, deformable local attention and flow similarity attention, constituting the dual attention mechanism, can derive the output features responsible for deformable- and occlusion-aware fusion, respectively. Besides, to maintain the pose and global position consistency in transferring, we design a pose normalization network for learning adaptive normalization from the target pose to the source person. Both qualitative and quantitative results show that our method outperforms state-of-the-art models in public iPER and DeepFashion datasets.