Deformable GANs for Pose-based Human Image Generation

TL;DR

This paper introduces a novel GAN-based method with deformable skip connections and a nearest-neighbour loss to generate realistic images of persons in new poses, outperforming previous approaches on benchmark datasets.

Contribution

It proposes deformable skip connections and a nearest-neighbour loss for pose-based human image generation, achieving state-of-the-art results.

Findings

Outperforms previous methods on benchmark datasets

Generates realistic person images in novel poses

Applicable to deformable object generation with keypoint detection

Abstract

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.