研究人员正在开发新的AI 3D空间推理方法，超越了目前在连续空间关系方面存在困难的视觉-语言模型。GeoLatent和Matisse引入了使用结构化潜在空间和基于证据的推理的新方法，以提高3D重建和理解的保真度和效率。还提出了一个名为SpatialReasoner的基准和框架，一个名为Active House-Scale Spatial Reasoning (AHSR)的新范例，在大型3D环境中表现优于现有模型。 AI
影响 这些3D空间推理的进步可以为机器人、虚拟现实和自主系统带来更复杂的AI应用。
排序理由 该集群包含多篇研究论文，详细介绍了3D空间推理和重建的新方法和基准。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2610.02091v1 Announce Type: cross Abstract: Despite progress in vision-language models, 3D spatial reasoning from 2D images remains challenging. Text-based methods describe intermediate geometry with discrete tokens, limiting fidelity for continuous spatial relations. Conti…
arXiv:2609.38746v1 Announce Type: new Abstract: How can a 3D reconstruction system acquire and retain useful information to understand the geometry of a scene from partial views under a limited computation budget? Existing active view acquisition methods typically estimate uncert…
arXiv:2512.03284v2 Announce Type: replace Abstract: Spatial reasoning in large-scale 3D environments remains challenging for current vision--language models, which are typically constrained to room-scale scenarios. We formalize Active House-Scale Spatial Reasoning (AHSR), a new p…