Interact3D: 交互式物体的组合3D生成
Interact3D: Compositional 3D Generation of Interactive Objects
AI总结：
提出Interact3D框架，通过统一3D引导场景、两阶段组合流水线（全局到局部几何对齐和基于SDF的优化）以及闭环智能体修正策略，从单张图像生成物理合理的交互式3D组合物体，解决遮挡和空间关系保持问题。
摘要：
3D生成领域的最新突破使得合成高保真度的单个资产成为可能。然而，从单张图像生成3D组合物体——特别是在遮挡情况下——仍然具有挑战性。现有方法常常在隐藏区域退化几何细节，并且未能保持底层物体-物体空间关系（OOR）。我们提出了一个新颖的框架Interact3D，旨在生成物理上合理的交互式3D组合物体。我们的方法首先利用先进的生成先验，通过统一的3D引导场景策划高质量的单体资产。为了物理上组合这些资产，我们随后引入了一个稳健的两阶段组合流水线。基于3D引导场景，主物体通过精确的全局到局部几何对齐（配准）进行锚定，而后续几何体则通过基于可微符号距离场（SDF）的优化进行集成，该优化显式惩罚几何交叉。为了减少具有挑战性的碰撞，我们进一步部署了一个闭环的智能体修正策略。视觉语言模型（VLM）自主分析组合场景的多视图渲染，制定有针对性的修正提示，并引导图像编辑模块迭代地自我修正生成流水线。大量实验表明，Interact3D成功生成了有希望的碰撞感知组合，具有改进的几何保真度和一致的空间关系。
英文摘要：
Recent breakthroughs in 3D generation have enabled the synthesis of high-fidelity individual assets. However, generating 3D compositional objects from single images--particularly under occlusions--remains challenging. Existing methods often degrade geometric details in hidden regions and fail to preserve the underlying object-object spatial relationships (OOR). We present a novel framework Interact3D designed to generate physically plausible interacting 3D compositional objects. Our approach first leverages advanced generative priors to curate high-quality individual assets with a unified 3D guidance scene. To physically compose these assets, we then introduce a robust two-stage composition pipeline. Based on the 3D guidance scene, the primary object is anchored through precise global-to-local geometric alignment (registration), while subsequent geometries are integrated using a differentiable Signed Distance Field (SDF)-based optimization that explicitly penalizes geometry intersections. To reduce challenging collisions, we further deploy a closed-loop, agentic refinement strategy. A Vision-Language Model (VLM) autonomously analyzes multi-view renderings of the composed scene, formulates targeted corrective prompts, and guides an image editing module to iteratively self-correct the generation pipeline. Extensive experiments demonstrate that Interact3D successfully produces promising collsion-aware compositions with improved geometric fidelity and consistent spatial relationships.
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。
