Progressive Pose Attention Transfer for Person Image Generation
This addresses pose transfer for person image generation, with potential applications in data augmentation for person re-identification, though it appears incremental.
The paper tackles person image generation by transferring poses while maintaining appearance and shape consistency, achieving more realistic-looking results validated on Market-1501 and DeepFashion datasets.
This paper proposes a new generative adversarial network for pose transfer, i.e., transferring the pose of a given person to a target pose. The generator of the network comprises a sequence of Pose-Attentional Transfer Blocks that each transfers certain regions it attends to, generating the person image progressively. Compared with those in previous works, our generated person images possess better appearance consistency and shape consistency with the input images, thus significantly more realistic-looking. The efficacy and efficiency of the proposed network are validated both qualitatively and quantitatively on Market-1501 and DeepFashion. Furthermore, the proposed architecture can generate training images for person re-identification, alleviating data insufficiency. Codes and models are available at: https://github.com/tengteng95/Pose-Transfer.git.