Omni123：通过统一文本到2D和3D生成探索有限3D数据的3D原生基础模型
Omni123: Exploring 3D Native Foundation Models with Limited 3D Data by Unifying Text to 2D and 3D Generation
AI总结：
Omni123通过统一文本到2D和3D生成，利用文本-图像-3D的跨模态一致性作为隐式约束，提升3D生成的几何一致性与语义对齐。
摘要：
近年来，多模态大语言模型在统一文本和图像的理解与生成中表现出色，但将其原生能力扩展到3D仍具挑战性，因3D数据有限。相比丰富的2D图像，高质量3D资产稀缺，导致3D合成约束不足。现有方法常依赖间接流程，在2D编辑后通过优化提升到3D，牺牲几何一致性。我们提出Omni123，一种原生3D基础模型，统一文本到2D和文本到3D生成于单一自回归框架中。关键见解是图像与3D之间的跨模态一致性可作为隐式结构约束。通过将文本、图像和3D表示为共享序列空间中的离散标记，模型利用丰富的2D数据作为几何先验来改进3D表示。我们引入交错的X-to-X训练范式，在异构配对数据集上协调多样化的跨模态任务，无需完全对齐的文本-图像-3D三元组。通过在自回归序列中遍历语义-视觉-几何循环（例如，文本到图像到3D到图像），模型联合强制语义对齐、外观保真度和多视图几何一致性。实验表明，Omni123显著提升了文本引导的3D生成和编辑，展示了向多模态3D世界模型扩展的可扩展路径。
英文摘要：
Recent multimodal large language models have achieved strong performance in unified text and image understanding and generation, yet extending such native capability to 3D remains challenging due to limited data. Compared to abundant 2D imagery, high-quality 3D assets are scarce, making 3D synthesis under-constrained. Existing methods often rely on indirect pipelines that edit in 2D and lift results into 3D via optimization, sacrificing geometric consistency. We present Omni123, a 3D-native foundation model that unifies text-to-2D and text-to-3D generation within a single autoregressive framework. Our key insight is that cross-modal consistency between images and 3D can serve as an implicit structural constraint. By representing text, images, and 3D as discrete tokens in a shared sequence space, the model leverages abundant 2D data as a geometric prior to improve 3D representations. We introduce an interleaved X-to-X training paradigm that coordinates diverse cross-modal tasks over heterogeneous paired datasets without requiring fully aligned text-image-3D triplets. By traversing semantic-visual-geometric cycles (e.g., text to image to 3D to image) within autoregressive sequences, the model jointly enforces semantic alignment, appearance fidelity, and multi-view geometric consistency. Experiments show that Omni123 significantly improves text-guided 3D generation and editing, demonstrating a scalable path toward multimodal 3D world models.
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。
