新的多智能体框架提升了零样本3D理解能力 · 跟踪2个来源

作者 PulseAugur 编辑部 · [2 个来源] · 2026-06-23 14:44

研究人员引入了一种新颖的协作式多智能体框架，用于零样本3D理解，解决了现有基于视频方法的一些局限性。该系统采用一个规划智能体来战略性地选择和补充视角，以及一个感知智能体来构建3D场景的结构化认知图。这个迭代过程，其中智能体之间相互提供反馈，显著提高了在ScanRefer、3D辅助对话和SQA3D等基准测试上的性能，取得了最先进的成果。 AI

影响该框架有望提升AI解释和与3D环境交互的能力，对机器人和增强现实等领域产生影响。

排序理由该集群描述了一篇关于用于3D理解的新颖框架的最新研究论文。

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.CV TIER_1 English(EN) · Wenxin Wang, Bo Zhang, Feng Chen, Zixuan Wang, Wen Li, Changsheng Li, Yinjie Lei · 2026-06-24 04:00

Agentic Collaborative Cognition for Zero-Shot 3D Understanding

arXiv:2606.24649v1 Announce Type: new Abstract: Recent advancements have explored agentic zero-shot 3D understanding by reformulating it as video keyframe understanding with Multimodal Large Language Models (MLLMs). However, existing methods face an intrinsic bottleneck due to th…
arXiv cs.CV TIER_1 English(EN) · Yinjie Lei · 2026-06-23 14:44

Agentic Collaborative Cognition for Zero-Shot 3D Understanding

Recent advancements have explored agentic zero-shot 3D understanding by reformulating it as video keyframe understanding with Multimodal Large Language Models (MLLMs). However, existing methods face an intrinsic bottleneck due to the finite observation perspectives inherent in vi…

报道来源 [2]

Agentic Collaborative Cognition for Zero-Shot 3D Understanding

Agentic Collaborative Cognition for Zero-Shot 3D Understanding

相关实体

相关话题