GenZI：零样本三维人-场景交互生成
GenZI: Zero-Shot 3D Human-Scene Interaction Generation
AI总结：
GenZI提出首个零样本三维人-场景交互生成方法，通过从大型视觉-语言模型蒸馏交互先验，结合文本提示和迭代优化，无需三维交互数据即可在多样场景中合成可控的三维人体姿态与形状。
摘要：
我们能否在不学习任何三维人-场景交互数据的情况下，合成与场景交互的三维人体？我们提出GenZI，这是首个生成三维人-场景交互的零样本方法。GenZI的关键在于我们从大型视觉-语言模型（VLM）中蒸馏交互先验，这些模型已经学习了丰富的二维人-场景组合语义空间。给定自然语言描述和三维场景中期望交互的粗略点位置，我们首先利用VLM想象合理的二维人体交互，并将其修复到场景的多个渲染视图中。然后，我们构建一个鲁棒的迭代优化过程，在二维交互假设一致性的引导下，合成场景中三维人体模型的姿态和形状。与现有的基于学习的方法相比，GenZI绕开了传统上对采集三维交互数据的需求，并允许通过易于使用的文本提示灵活控制三维交互合成。大量实验表明，我们的零样本方法具有很高的灵活性和通用性，使其适用于包括室内和室外环境在内的多种场景类型。
英文摘要：
Can we synthesize 3D humans interacting with scenes without learning from any 3D human-scene interaction data? We propose GenZI, the first zero-shot approach to generating 3D human-scene interactions. Key to GenZI is our distillation of interaction priors from large vision-language models (VLMs), which have learned a rich semantic space of 2D human-scene compositions. Given a natural language description and a coarse point location of the desired interaction in a 3D scene, we first leverage VLMs to imagine plausible 2D human interactions inpainted into multiple rendered views of the scene. We then formulate a robust iterative optimization to synthesize the pose and shape of a 3D human model in the scene, guided by consistency with the 2D interaction hypotheses. In contrast to existing learning-based approaches, GenZI circumvents the conventional need for captured 3D interaction data, and allows for flexible control of the 3D interaction synthesis with easy-to-use text prompts. Extensive experiments show that our zero-shot approach has high flexibility and generality, making it applicable to diverse scene types, including both indoor and outdoor environments.
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。
