MUNCH: Modelling Unique 'N Controllable Heads

TL;DR

This paper introduces MUNCH, a controllable 3D head generation method that offers high quality, diversity, and explainability, enabling artists to manipulate shape and texture with semantic control and novel metrics for evaluation.

Contribution

MUNCH presents a novel disentangled latent space for shape and texture, a physically-based render map synthesis, and a semantic color control mechanism for 3D head generation.

Findings

High diversity and quality in generated heads

Effective semantic control over textures

Introduction of Uniqueness and Novelty metrics

Abstract

The automated generation of 3D human heads has been an intriguing and challenging task for computer vision researchers. Prevailing methods synthesize realistic avatars but with limited control over the diversity and quality of rendered outputs and suffer from limited correlation between shape and texture of the character. We propose a method that offers quality, diversity, control, and realism along with explainable network design, all desirable features to game-design artists in the domain. First, our proposed Geometry Generator identifies disentangled latent directions and generate novel and diverse samples. A Render Map Generator then learns to synthesize multiply high-fidelty physically-based render maps including Albedo, Glossiness, Specular, and Normals. For artists preferring fine-grained control over the output, we introduce a novel Color Transformer Model that allows semantic color control over generated maps. We also introduce quantifiable metrics called Uniqueness and Novelty and a combined metric to test the overall performance of our model. Demo for both shapes and textures can be found: https://munch-seven.vercel.app/. We will release our model along with the synthetic dataset.