Spectral normalization and relativistic adversarial training for conditional pose generation with self-attention

We address the problem of conditional image generation of synthesizing a new image of an individual given a reference image and target pose. We base our approach on generative adversarial networks and leverage deformable skip connections to deal with pixel-to-pixel misalignments, self-attention to leverage complementary features in separate portions of the image, e.g., arms or legs, and spectral normalization to improve the quality of the synthesized images. We train the synthesis model with a nearest-neighbour loss in combination with a relativistic average hinge adversarial loss. We evaluate on the Market-1501 dataset and show how our proposed approach can surpass existing approaches in conditional image synthesis performance.