EasyCraft: A Robust and Efficient Framework for Automatic Avatar Crafting

2025-03-03

AI Summary

Existing character customization methods suffer from limited generalizability due to reliance on unimodal input (text-only or image-only) and engine-specific constraints. This work proposes EasyCraft, an end-to-end feedforward framework featuring a novel dual-modality translatable architecture that jointly supports both textual and visual inputs. By leveraging self-supervised feature learning, EasyCraft constructs a cross-domain consistent latent face space, effectively disentangling stylistic representations from engine-specific parameter mappings. The method enables zero-shot adaptation across heterogeneous game engines (e.g., Unity and Unreal) without retraining. Evaluated on two RPG games, EasyCraft achieves state-of-the-art performance in translating arbitrary-style facial images into high-fidelity, robust crafting parameters. It significantly enhances the universality and practicality of personalized avatar generation, offering broad compatibility with diverse input modalities and rendering backends.

Technology Category

• Humans and AI: Game Design — Virtual Humans, NPCs and Autonomous Characters
• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Machine Learning: Multimodal Learning

Application Category

• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

Abstract

Character customization, or 'face crafting,' is a vital feature in role-playing games (RPGs), enhancing player engagement by enabling the creation of personalized avatars. Existing automated methods often struggle with generalizability across diverse game engines due to their reliance on the intermediate constraints of specific image domain and typically support only one type of input, either text or image. To overcome these challenges, we introduce EasyCraft, an innovative end-to-end feedforward framework that automates character crafting by uniquely supporting both text and image inputs. Our approach employs a translator capable of converting facial images of any style into crafting parameters. We first establish a unified feature distribution in the translator's image encoder through self-supervised learning on a large-scale dataset, enabling photos of any style to be embedded into a unified feature representation. Subsequently, we map this unified feature distribution to crafting parameters specific to a game engine, a process that can be easily adapted to most game engines and thus enhances EasyCraft's generalizability. By integrating text-to-image techniques with our translator, EasyCraft also facilitates precise, text-based character crafting. EasyCraft's ability to integrate diverse inputs significantly enhances the versatility and accuracy of avatar creation. Extensive experiments on two RPG games demonstrate the effectiveness of our method, achieving state-of-the-art results and facilitating adaptability across various avatar engines.

Problem

• Automates avatar creation with text and image inputs.
• Enhances generalizability across diverse game engines.
• Improves versatility and accuracy in character customization.

Innovation

• Supports both text and image inputs
• Unified feature distribution via self-supervised learning
• Adaptable to most game engines