TL
TL;DR
The problem of reposing an image of a human into any desired novel pose is addressed and a dense feature volume is implicitly learned from human images, which lends itself to simple and intuitive manipulation through explicit geometric warping.
Abstract
We address the problem of reposing an image of a human into any desired novel pose. This conditional image-generation task requires reasoning about the 3D structure of the human, including self-occluded body parts. Most prior works are either based on 2D representations or require fitting and manipulating an explicit 3D body mesh. Based on the recent success in deep learning-based volumetric representations, we propose to implicitly learn a dense feature volume from human images, which lends itself to simple and intuitive manipulation through explicit geometric warping. Once the latent feature volume is warped according to the desired pose change, the volume is mapped back to RGB space by a convolutional decoder.Our state-of-the-art results on the DeepFashion and the iPER benchmarks indicate that dense volumetric human representations are worth investigating in more detail.
References42 items
1
Generative Adversarial Networks
2
Metric-Scale Truncation-Robust Heatmaps for 3D Human Pose Estimation
3
Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesis
4
Coordinate-Based Texture Inpainting for Pose-Guided Human Image Generation
5