研究人员开发了 DepthAgent，这是一种新颖的视觉语言代理，旨在改进各种相机类型的单目深度估计。与使用单一估计器之前的其他方法不同，DepthAgent 利用多个预先存在的深度模型作为工具。它智能地分析场景和相机几何结构，以选择或融合这些专家的预测，尤其是在单个模型表现不佳的挑战性样本上表现出色。这种自适应方法显著提高了深度估计任务的准确性和鲁棒性。 AI
影响 通过自适应地选择和融合多个专家模型，提高了跨不同相机几何结构的深度估计准确性和鲁棒性。
排序理由 该集群包含一篇详细介绍深度估计新方法的论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2605.23281v1 Announce Type: new Abstract: Monocular metric depth estimation has achieved strong progress with large-scale training and universal-camera modeling, yet robust deployment across diverse camera settings, such as perspective, fisheye, and panoramic images, remain…
Monocular metric depth estimation has achieved strong progress with large-scale training and universal-camera modeling, yet robust deployment across diverse camera settings, such as perspective, fisheye, and panoramic images, remains challenging. Existing methods typically rely o…