ComboVerse：使用空间感知扩散引导的组合式3D资产生成
ComboVerse: Compositional 3D Assets Creation Using Spatially-Aware Diffusion Guidance
AI总结：
提出ComboVerse框架，通过分析多物体差距并利用空间感知分数蒸馏采样（SSDS）指导多模型空间定位，实现高质量组合式3D资产生成。
摘要：
从给定图像生成高质量3D资产在AR/VR等各种应用中极具吸引力。单图像3D生成的最新进展探索了前馈模型，这些模型学习在无需优化的情况下推断物体的3D模型。尽管在单物体生成方面取得了可喜的成果，但这些方法在建模本质上包含多个物体的复杂3D资产时往往显得力不从心。在本研究中，我们提出了ComboVerse，这是一个3D生成框架，通过学习组合多个模型来生成具有复杂组合的高质量3D资产。1）我们首先从模型和数据角度深入分析了这种“多物体差距”。2）接着，利用不同物体的重建3D模型，我们寻求调整它们的大小、旋转角度和位置，以创建与给定图像匹配的3D资产。3）为使该过程自动化，我们从预训练扩散模型中应用空间感知分数蒸馏采样（SSDS）来指导物体的定位。我们提出的框架强调物体的空间对齐，与标准分数蒸馏采样相比，从而实现了更准确的结果。大量实验验证了ComboVerse在生成组合式3D资产方面相比现有方法取得了明显改进。
英文摘要：
Generating high-quality 3D assets from a given image is highly desirable in various applications such as AR/VR. Recent advances in single-image 3D generation explore feed-forward models that learn to infer the 3D model of an object without optimization. Though promising results have been achieved in single object generation, these methods often struggle to model complex 3D assets that inherently contain multiple objects. In this work, we present ComboVerse, a 3D generation framework that produces high-quality 3D assets with complex compositions by learning to combine multiple models. 1) We first perform an in-depth analysis of this ``multi-object gap'' from both model and data perspectives. 2) Next, with reconstructed 3D models of different objects, we seek to adjust their sizes, rotation angles, and locations to create a 3D asset that matches the given image. 3) To automate this process, we apply spatially-aware score distillation sampling (SSDS) from pretrained diffusion models to guide the positioning of objects. Our proposed framework emphasizes spatial alignment of objects, compared with standard score distillation sampling, and thus achieves more accurate results. Extensive experiments validate ComboVerse achieves clear improvements over existing methods in generating compositional 3D assets.
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。
