This paper presents a novel generative adversarial network for the task of human pose transfer, which aims at transferringthe pose of a given person to a target pose. In order to deal with pixel-to-pixel misalignment due to the pose differences, weintroduce an attention mechanism and propose Pose-Guided Attention Blocks. With these blocks, the generator can learnhow to transfer the details from the conditional image to the target image based on the target pose. Our network can makethe target pose truly guide the transfer of features. The effectiveness of the proposed network is validated on DeepFasionand Market-1501 datasets. Compared with state-of-the-art methods, our generated images are more realistic with betterfacial details.
展开▼