High-Fidelity Neural Human Motion Transfer from Monocular Video

TL;DR

This paper introduces a novel neural framework for high-fidelity, temporally consistent human motion transfer from monocular videos, effectively capturing clothing dynamics and pose-dependent details for realistic video synthesis.

Contribution

The authors propose a three-stage image generation approach with recurrent neural networks that improves realism and temporal consistency in human motion transfer, especially for loose garments.

Findings

Outperforms state-of-the-art in video realism

Handles clothing dynamics and pose-dependent details effectively

Provides artistic control over generated results

Abstract

Video-based human motion transfer creates video animations of humans following a source motion. Current methods show remarkable results for tightly-clad subjects. However, the lack of temporally consistent handling of plausible clothing dynamics, including fine and high-frequency details, significantly limits the attainable visual quality. We address these limitations for the first time in the literature and present a new framework which performs high-fidelity and temporally-consistent human motion transfer with natural pose-dependent non-rigid deformations, for several types of loose garments. In contrast to the previous techniques, we perform image generation in three subsequent stages, synthesizing human shape, structure, and appearance. Given a monocular RGB video of an actor, we train a stack of recurrent deep neural networks that generate these intermediate representations from 2D poses and their temporal derivatives. Splitting the difficult motion transfer problem into subtasks that are aware of the temporal motion context helps us to synthesize results with plausible dynamics and pose-dependent detail. It also allows artistic control of results by manipulation of individual framework stages. In the experimental results, we significantly outperform the state-of-the-art in terms of video realism. Our code and data will be made publicly available.