UnfoldArt: 从文本或图像零样本恢复完整关节式3D物体
UnfoldArt: Zero-Shot Recovery of Full Articulated 3D Objects from Text or Image
AI总结：
提出首个辩论驱动代理方法，结合视觉语言模型和视频生成先验，从文本或图像零样本重建关节式3D物体的结构、运动与隐藏几何。
摘要：
关节式3D物体对于具身AI、机器人技术和虚拟现实中的交互环境至关重要，但从稀疏观测中重建其结构和运动仍然具有挑战性。现有方法大多受限于缺乏监督数据或缺乏可靠恢复关节、隐藏几何和内部物体结构所需的先验知识。我们提出了首个辩论驱动的代理方法，用于从文本或图像输入重建关节式3D物体，该方法既将关节推理具体化为具体运动，又揭示了关节下暴露的遮挡几何。高层代理使用视觉语言和视频模型的知识推理物体语义和运动，而低层代理估计关节参数和交互点；它们共同参与两轮结构化辩论，首先利用全局-局部不一致性，然后将代理基于自由生成的视频。相同的视频先验，以商定的关节为条件，然后驱动每个部分通过其运动，以暴露无法从单个静态视图推断的遮挡内部和几何。通过将代理推理与视频生成先验相结合，我们的方法联合推断关节并重建完整的3D关节式物体，生成高保真几何、内部结构和运动一致状态，超越直接观察到的表面。
英文摘要：
Articulated 3D objects are essential for interactive environments in embodied AI, robotics, and virtual reality, but reconstructing their structure and motion from sparse observations remains challenging. Existing approaches remain largely constrained by lack of supervised data or lack the priors needed to reliably recover articulation, hidden geometry, and internal object structure. We present the first debate-driven agentic approach to articulated 3D object reconstruction from text or image inputs that both grounds articulation reasoning in concrete motion and exposes the occluded geometry revealed under articulation. High-level agents reason about object semantics and motion using knowledge from vision-language and video models, while low-level agents estimate articulation parameters and interaction points; together, they engage in a two-round structured debate that first exploits global--local disagreement and then grounds the agents in freely generated video. The same video prior, conditioned on the agreed articulation, then drives each part through its motion to expose occluded interiors and geometry that cannot be inferred from a single static view. By combining agentic reasoning with a video generative prior, our approach jointly infers articulation and reconstructs complete 3D articulated objects, producing high-fidelity geometry, internal structure, and motion-consistent states beyond directly observed surfaces.
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。
