English(EN) InHabit: Leveraging Image Foundation Models for Scalable 3D Human Placement

新系统InHabit生成大规模3D人景交互数据

作者 PulseAugur 编辑部 · [1 个来源] · 2026-05-27 04:00

研究人员开发了InHabit，一个用于生成大规模、照片级逼真的人类与环境交互的3D数据集的新颖系统。该系统利用图像基础模型来提出动作并将人类插入3D场景，然后将这些插入细化为物理上合理的SMPL-X身体。由此产生的数据集InHabitants包含约800个场景中的78,000个样本，并在3D人类场景重建和接触估计任务中展示了改进。 AI

排序理由该集群描述了一篇详细介绍新合成数据生成方法的最新研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

报道来源 [1]

arXiv cs.CV TIER_1 English(EN) · Nikita Kister, Pradyumna YM, Istv\'an S\'ar\'andi, Jiayi Wang, Anna Khoreva, Gerard Pons-Moll · 2026-05-27 04:00

InHabit: Leveraging Image Foundation Models for Scalable 3D Human Placement

arXiv:2604.19673v2 Announce Type: replace Abstract: Training embodied agents to understand 3D scenes as humans do requires large-scale data of people meaningfully interacting with diverse environments, yet such data is scarce. Real-world capture is costly and limited to controlle…

报道来源 [1]

InHabit: Leveraging Image Foundation Models for Scalable 3D Human Placement

相关话题