Deformable GANs for Pose-based Human Image Generation

In this paper we address the problem of generating person images conditionedon a given pose. Specifically, given an image of a person and a target pose, wesynthesize a new image of that person in the novel pose. In order to deal withpixel-to-pixel misalignments caused by the pose differences, we introducedeformable skip connections in the generator of our Generative AdversarialNetwork. Moreover, a nearest-neighbour loss is proposed instead of the commonL1 and L2 losses in order to match the details of the generated image with thetarget image. We test our approach using photos of persons in different posesand we compare our method with previous work in this area showingstate-of-the-art results in two benchmarks. Our method can be applied to thewider field of deformable object generation, provided that the pose of thearticulated object can be extracted using a keypoint detector.