Human Pose Manipulation and Novel View Synthesis using Differentiable Rendering

Note: We don't have the ability to review paper

PubDate: January 2022

Teams: University of Surrey;AWS Tübingen

Writers: Guillaume Rochette; Chris Russell; Richard Bowden

PDF: Human Pose Manipulation and Novel View Synthesis using Differentiable Rendering

Abstract

We present a new approach for synthesizing novel views of people in new poses. Our novel differentiable renderer enables the synthesis of highly realistic images from any viewpoint. Rather than operating over mesh-based structures, our renderer makes use of diffuse Gaussian primitives that directly represent the underlying skeletal structure of a human. Rendering these primitives gives results in a high-dimensional latent image, which is then transformed into an RGB image by a decoder network. The formulation gives rise to a fully differentiable framework that can be trained end-to-end. We demonstrate the effectiveness of our approach to image reconstruction on both the Human3.6M and Panoptic Studio datasets. We show how our approach can be used for motion transfer between individuals; novel view synthesis of individuals captured from just a single camera; to synthesize individuals from any virtual viewpoint; and to re-render people in novel poses. Code and video results are available at https://github.com/GuillaumeRochette/HumanViewSynthesis.

You may also like...

Paper