Multiface: A Dataset for Neural Face Rendering

TL;DR

Multiface is a high-resolution multi-view face dataset designed to advance neural face rendering research, enabling better synthesis of novel viewpoints and expressions with improved model architectures.

Contribution

The paper introduces Multiface, a new publicly available high-quality multi-view face dataset and evaluates model improvements for neural face rendering.

Findings

Adding spatial bias enhances view interpolation.

Texture warp fields improve expression synthesis.

Residual connections boost model performance.

Abstract

Photorealistic avatars of human faces have come a long way in recent years, yet research along this area is limited by a lack of publicly available, high-quality datasets covering both, dense multi-view camera captures, and rich facial expressions of the captured subjects. In this work, we present Multiface, a new multi-view, high-resolution human face dataset collected from 13 identities at Reality Labs Research for neural face rendering. We introduce Mugsy, a large scale multi-camera apparatus to capture high-resolution synchronized videos of a facial performance. The goal of Multiface is to close the gap in accessibility to high quality data in the academic community and to enable research in VR telepresence. Along with the release of the dataset, we conduct ablation studies on the influence of different model architectures toward the model's interpolation capacity of novel viewpoint and expressions. With a conditional VAE model serving as our baseline, we found that adding spatial bias, texture warp field, and residual connections improves performance on novel view synthesis. Our code and data is available at: https://github.com/facebookresearch/multiface