Geometry-Aware Texture Generation for 3D Head Modeling with Artist-driven Control

2025-05-07

AI Summary

This work addresses the challenge of high-fidelity 3D human head modeling in virtual character creation, where precise artistic control remains difficult and editing workflows are labor-intensive. We propose a geometry-aware texture synthesis framework enabling artists to manipulate global geometry, skin-tone distribution, and fine-scale wrinkles/hair details—hierarchically and controllably—from a single input texture map, while automatically enforcing cross-channel consistency. Our core technical contributions include: (1) geometry-guided multimodal feature learning; (2) demographic-aware texture mapping; and (3) single-image-driven, cross-channel collaborative editing. Experiments demonstrate that the synthesized models exhibit clean, well-structured geometry and rich, diverse textures. The method significantly streamlines practical pipelines—including scan retopology, repair, and age-related detail augmentation—and validates its efficiency and strong controllability in real-world production environments.

Technology Category

• Humans and AI: Game Design — Virtual Humans, NPCs and Autonomous Characters
• Computer Vision: Diffusion Models for Vision
• Cognitive Modeling & Cognitive Systems: Computational Creativity

Application Category

• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Creating realistic 3D head assets for virtual characters that match a precise artistic vision remains labor-intensive. We present a novel framework that streamlines this process by providing artists with intuitive control over generated 3D heads. Our approach uses a geometry-aware texture synthesis pipeline that learns correlations between head geometry and skin texture maps across different demographics. The framework offers three levels of artistic control: manipulation of overall head geometry, adjustment of skin tone while preserving facial characteristics, and fine-grained editing of details such as wrinkles or facial hair. Our pipeline allows artists to make edits to a single texture map using familiar tools, with our system automatically propagating these changes coherently across the remaining texture maps needed for realistic rendering. Experiments demonstrate that our method produces diverse results with clean geometries. We showcase practical applications focusing on intuitive control for artists, including skin tone adjustments and simplified editing workflows for adding age-related details or removing unwanted features from scanned models. This integrated approach aims to streamline the artistic workflow in virtual character creation.

Problem

• Streamlining 3D head modeling with artist-driven control
• Learning geometry-texture correlations for diverse demographics
• Enabling intuitive multi-level texture and geometry editing

Innovation

• Geometry-aware texture synthesis pipeline
• Three-level artistic control framework
• Automatic coherent texture map propagation