Human Pose Manipulation and Novel View Synthesis using Differentiable Rendering

TL;DR

This paper introduces a differentiable rendering method using Gaussian primitives for realistic human pose manipulation and novel view synthesis, enabling end-to-end training and diverse applications.

Contribution

A novel differentiable renderer based on Gaussian primitives that directly models human skeletal structure for improved view synthesis and pose editing.

Findings

Effective image reconstruction on Human3.6M and Panoptic datasets

Enables motion transfer and pose editing from a single camera

Produces realistic images from arbitrary viewpoints

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.