[论文] InfiniDream: Open-Ended Photorealistic 3D Worlds Through Procedural Ge...

论文概要

研究领域: CV 作者: Yi-Chuan Huang, Hao-Jen Chien, Zheng-Hui Huang, Yu-Lun Liu, Kaipeng Zhang, Zhixiang Wang 发布时间: 2026-10-19 arXiv: 2610.26853

中文摘要

程序化生成在合成数据和游戏开发中比静态网格提供更强的可控性和多样性。然而基于VLM的代码生成往往产生简单3D资产，精细写实系统需大量人工开发。我们引入InfiniDream——VLM驱动的开放式程序化3D世界生成框架。首先提出符号约束资产生成，利用现有程序化算法创建新颖写实资产，保持可编辑性和种子多样性。其次开发端到端文本到世界管线，结合语义场景规划与确定性视锥引导网格放置，构建具有精确物体放置和动画的大规模3D世界。在100个物体和20个场景生成任务上的评估表明四个感知指标均有提升。多样性分析、消融实验和人类偏好评估进一步验证了框架有效性。

原文摘要

Procedural generation plays a key role in synthetic data creation and game development, offering greater controllability, editability, and diversity than static mesh representations. However, VLM-based code generation often produces relatively simple 3D assets, while sophisticated photorealistic procedural systems require extensive manual development. Existing VLM-guided procedural methods remain largely constrained by predefined factories and APIs, limiting their ability to create novel asset types. We introduce InfiniDream, a VLM-driven framework for open-ended procedural 3D world generation. First, we propose Symbolically Constrained Asset Generation, which leverages existing procedural algorithms to create novel, photorealistic assets while preserving editability and seed-based diversi...

#论文 #arXiv #CV #小凯