用文本生成可组合的3D模型，提升设计效率与多样性。
AssetFormer: Modular 3D Assets Generation with Autoregressive Transformer
- 基于自回归Transformer，按模块顺序生成3D资产。
- 支持约束条件下多样化的模块组合，提升生成质量。
- 适合游戏、设计等需要快速生成3D内容的场景。
数字产业对高质量、多样化的模块化3D资产需求日益增长，尤其在用户生成内容（UGC）领域。本文提出AssetFormer，一种基于自回归Transformer的模型，可根据文本描述生成模块化3D资产。通过分析真实平台收集的模块化资产数据，AssetFormer解决了在受限设计参数下生成由基础组件构成的复杂资产的挑战。受语言模型启发，创新性地采用模块序列建模与解码策略，通过自回归机制提升生成质量。初步实验表明，该方法在专业开发与UGC场景中显著简化了资产创建流程。本工作提供了一个可扩展至多种模块化3D资产的灵活框架，推动3D内容生成技术发展。代码已开源：https://github.com/Advocate99/AssetFormer。
原文摘要 · Abstract (English)
The digital industry demands high-quality, diverse modular 3D assets, especially for user-generated content~(UGC). In this work, we introduce AssetFormer, an autoregressive Transformer-based model designed to generate modular 3D assets from textual descriptions. Our pilot study leverages real-world modular assets collected from online platforms. AssetFormer tackles the challenge of creating assets composed of primitives that adhere to constrained design parameters for various applications. By innovatively adapting module sequencing and decoding techniques inspired by language models, our approach enhances asset generation quality through autoregressive modeling. Initial results indicate the effectiveness of AssetFormer in streamlining asset creation for professional development and UGC scenarios. This work presents a flexible framework extendable to various types of modular 3D assets, contributing to the broader field of 3D content generation. The code is available at https://github.com/Advocate99/AssetFormer.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。