Neural Human Video Rendering by Learning Dynamic Textures and Rendering-to-Video Translation

TL;DR

This paper introduces a neural human video synthesis method that explicitly models dynamic textures and uses a dual CNN approach to improve temporal coherence and detail preservation in generated videos.

Contribution

It proposes a novel approach that disentangles fine-scale detail learning from 2D embedding, enhancing realism and temporal stability in human video synthesis.

Findings

Significant improvement over state-of-the-art in qualitative quality

Quantitative metrics show better detail and temporal consistency

Effective for human reenactment and view synthesis from monocular videos

Abstract

Synthesizing realistic videos of humans using neural networks has been a popular alternative to the conventional graphics-based rendering pipeline due to its high efficiency. Existing works typically formulate this as an image-to-image translation problem in 2D screen space, which leads to artifacts such as over-smoothing, missing body parts, and temporal instability of fine-scale detail, such as pose-dependent wrinkles in the clothing. In this paper, we propose a novel human video synthesis method that approaches these limiting factors by explicitly disentangling the learning of time-coherent fine-scale details from the embedding of the human in 2D screen space. More specifically, our method relies on the combination of two convolutional neural networks (CNNs). Given the pose information, the first CNN predicts a dynamic texture map that contains time-coherent high-frequency details, and the second CNN conditions the generation of the final video on the temporally coherent output of the first CNN. We demonstrate several applications of our approach, such as human reenactment and novel view synthesis from monocular video, where we show significant improvement over the state of the art both qualitatively and quantitatively.