Reposing Humans by Warping 3D Features
This addresses the challenge of realistic human image reposing for applications like virtual try-on or animation, though it is incremental by building on existing volumetric representations.
The paper tackles the problem of reposing human images into novel poses by learning a dense 3D feature volume from images and warping it geometrically, achieving state-of-the-art results on DeepFashion and iPER benchmarks.
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.