研究人员开发了从单张图像生成和编辑3D场景的新框架。SceneConductor将过程分解为初始化、环境构建和多智能体优化，提高了几何精度和真实感。SceneCompleter使用几何感知扩散模型进行新视角合成，专注于密集3D场景补全，解决了几何失真和外观漂移的问题。MUSE通过基于记忆的增量需求满足提供智能体3D场景创作，实现了可控构建和保留感知编辑。 AI
影响 这些3D场景生成和编辑方面的进展可以加速虚拟环境和AI模拟的内容创建。
排序理由 该集群包含多篇学术论文，详细介绍了用于3D场景生成和编辑的新研究框架。
在 arXiv cs.MA (Multiagent) 阅读 →
AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →
Generating complete 3D scenes from a single image requires inferring globally consistent geometry, object relationships, and environmental context from inherently ambiguous visual evidence. Despite recent progress in joint layout-and-mesh generation, existing methods often rely o…
arXiv:2506.10981v2 Announce Type: replace Abstract: Generative models have shown great promise for novel view synthesis (NVS) by leveraging strong image generation priors. However, existing approaches typically follow a 2D inpainting paradigm, first completing missing image regio…
arXiv:2606.14168v1 Announce Type: new Abstract: Text-driven 3D scene generation is a promising technique for digital content creation, embodied AI simulation, and interactive design, yet practical workflows often require refining, extending, or correcting existing scenes while pr…
Text-driven 3D scene generation is a promising technique for digital content creation, embodied AI simulation, and interactive design, yet practical workflows often require refining, extending, or correcting existing scenes while preserving non-target content. Existing methods ca…