English(EN) ESG: Generating Physically Consistent Dynamic 3D Scenes from Text Descriptions

新框架从文本生成具有物理一致性的动态3D场景

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-15 04:00

研究人员开发了一个名为ESG（Evolutive Scene Graph）的新框架，该框架可以根据文本描述生成动态3D场景，确保物理一致性并可在Unreal Engine中直接执行。该方法涉及一个大型语言模型构建一个包含物理属性和事件驱动时间线的实体机器可检查图。该系统通过可微分仿真优化空间布局和物理参数，以满足用户指定的事件，在事件完成度和参数准确性方面优于现有基线。 AI

影响为游戏和仿真等应用实现更真实、更具交互性的3D环境。

排序理由详细介绍一种新动态3D场景生成方法的学术论文。[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: 14 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍一种新动态3D场景生成方法的学术论文。[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, product; 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) · Xintong Fang, Zhiyuan Fang, Rengan Xie, Xuhong Zhang, Guoyuan An, Zeran Liu, Jingyan Zhang, Jiarui Guo, Yuchi Huo · 2026-09-15 04:00

ESG：从文本描述生成物理上一致的动态三维场景

arXiv:2609.15392v1 Announce Type: cross Abstract: Recent progress in image and 3D scene generation has enabled increasingly realistic static environments, yet most methods remain confined to such static configurations. Generating dynamic scenes from natural language is fundamenta…

本文如何被排名

报道来源 [1]

ESG：从文本描述生成物理上一致的动态三维场景

相关实体

相关话题