Deformable GANs for Pose-based Human Image Generation

Aliaksandr Siarohin (1) , Enver Sangineto (1) , Stéphane Lathuilière (2) , Nicu Sebe (1)

1 DISI - Department of Information Engineering and Computer Science (University of Trento )
2 PERCEPTION - Interpretation and Modelling of Images and Videos

In this paper we address the problem of generating person images conditioned on a given pose. Specifically, given an image of a person and a target pose, we synthesize a new image of that person in the novel pose. In order to deal with pixel-to-pixel misalignments caused by the pose differences, we introduce deformable skip connections in the generator of our Generative Adversarial Network. Moreover, a nearest-neighbour loss is proposed instead of the common L1 and L2 losses in order to match the details of the generated image with the target image. We test our approach using photos of persons in different poses and we compare our method with previous work in this area showing state-of-the-art results in two benchmarks. Our method can be applied to the wider field of deformable object generation, provided that the pose of the articulated object can be extracted using a keypoint detector.

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]; Traitement du signal et de l'image [eess.SP]; Apprentissage [cs.LG]

Aliaksandr Siarohin, Enver Sangineto, Stéphane Lathuilière, Nicu Sebe. Deformable GANs for Pose-based Human Image Generation. IEEE Conference on Computer Vision and Pattern Recognition, Jun 2018, Salt Lake City, United States. pp.3408-3416, ⟨10.1109/CVPR.2018.00359⟩. ⟨hal-01761539⟩