English(EN) NeoWorld-Pro: Programming Interactive Scenes from Monocular Images for Embodied Simulation

MLLMs 将图像转换为具有物理基础的交互式 3D 场景

作者 PulseAugur 编辑部 · [1 个来源] · 2026-08-26 04:00

研究人员开发了 NeoWorld-Pro，一个使用多模态大语言模型 (MLLMs) 将单个 RGB 图像转换为交互式 3D 环境的可执行程序的框架。该方法将场景重建重新表述为过程式编程，能够指定对象的几何形状、关节和物理属性。一个物理闭环机制通过在物理引擎中验证程序的执行来完善这些程序，确保物理上合理的交互和准确的空间关系。在稳定堆叠和精细操作等任务中，NeoWorld-Pro 的性能优于现有方法。 AI

影响通过将 3D 场景生成与物理属性相结合，为具身 AI 研究实现更真实、更具交互性的模拟。

排序理由该集群描述了一篇关于使用 MLLMs 和物理模拟进行场景重建的新颖框架的最新研究论文。[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 →

本文如何被排名

Signal score: 34 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群描述了一篇关于使用 MLLMs 和物理模拟进行场景重建的新颖框架的最新研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, infra; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CV TIER_1 English(EN) · Yumeng He, Yichen Song, Xiaotian Yang, Weijia Zhang, Zanwei Zhou, Junru Gong, Xiaokang Yang, Yunbo Wang · 2026-08-26 04:00

NeoWorld-Pro：从单目图像中为具身模拟编程交互式场景

arXiv:2608.24212v1 Announce Type: new Abstract: The advancement of Embodied AI necessitates high-quality simulation assets that faithfully mirror the real world. However, transforming raw visual observations into simulation-ready scenes remains challenging due to the lack of phys…

本文如何被排名

报道来源 [1]

NeoWorld-Pro：从单目图像中为具身模拟编程交互式场景

相关实体

相关话题