PhoMoH: Implicit Photorealistic 3D Models of Human Heads

TL;DR

PhoMoH introduces a neural network approach to generate highly detailed, photorealistic 3D human head models with complex topology, leveraging existing head models and neural fields for enhanced realism and diversity.

Contribution

The paper presents a novel neural field-based method to augment existing head models with detailed geometry and appearance, supporting complex topology and requiring less data.

Findings

Enables generation of diverse, realistic 3D human heads.

Supports complex topology with neural fields.

Validated through extensive qualitative and quantitative experiments.

Abstract

We present PhoMoH, a neural network methodology to construct generative models of photo-realistic 3D geometry and appearance of human heads including hair, beards, an oral cavity, and clothing. In contrast to prior work, PhoMoH models the human head using neural fields, thus supporting complex topology. Instead of learning a head model from scratch, we propose to augment an existing expressive head model with new features. Concretely, we learn a highly detailed geometry network layered on top of a mid-resolution head model together with a detailed, local geometry-aware, and disentangled color field. Our proposed architecture allows us to learn photo-realistic human head models from relatively little data. The learned generative geometry and appearance networks can be sampled individually and enable the creation of diverse and realistic human heads. Extensive experiments validate our method qualitatively and across different metrics.