ThemeStation：从少量样例生成具备主题感知能力的3D资产
ThemeStation: Generating Theme-Aware 3D Assets from Few Exemplars
AI总结：
针对少量样例下主题一致的定制化3D资产生成难题，提出ThemeStation两阶段框架与双分数蒸馏损失，在保证主题一致性的同时提升生成多样性，效果优于现有方法并支持多种应用。
摘要：
现实应用通常需要大量共享统一主题的3D资产库。尽管通用的文本或图像驱动3D内容生成已取得显著进展，但根据输入3D样例的共享主题合成定制化3D资产仍是一个开放且具挑战性的问题。本文提出ThemeStation，一种用于主题感知3D到3D生成的新方法。ThemeStation基于给定的少量样例合成定制化3D资产，兼顾两个目标：1）一致性，生成的3D资产与给定样例在主题上保持一致；2）多样性，生成的3D资产具备高度变化性。为此，我们设计了一个两阶段框架：首先生成概念图像，随后进入参考引导的3D建模阶段。我们提出一种新型双分数蒸馏（DSD）损失，以联合利用输入样例和合成概念图像的先验信息。大量实验和用户研究证实，ThemeStation在生成多样化、高质量的主题感知3D模型方面优于现有方法。ThemeStation还支持可控3D到3D生成等多种应用。
英文摘要：
Real-world applications often require a large gallery of 3D assets that share a consistent theme. While remarkable advances have been made in general 3D content creation from text or image, synthesizing customized 3D assets following the shared theme of input 3D exemplars remains an open and challenging problem. In this work, we present ThemeStation, a novel approach for theme-aware 3D-to-3D generation. ThemeStation synthesizes customized 3D assets based on given few exemplars with two goals: 1) unity for generating 3D assets that thematically align with the given exemplars and 2) diversity for generating 3D assets with a high degree of variations. To this end, we design a two-stage framework that draws a concept image first, followed by a reference-informed 3D modeling stage. We propose a novel dual score distillation (DSD) loss to jointly leverage priors from both the input exemplars and the synthesized concept image. Extensive experiments and user studies confirm that ThemeStation surpasses prior works in producing diverse theme-aware 3D models with impressive quality. ThemeStation also enables various applications such as controllable 3D-to-3D generation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
