MD2E：面向单目度量深度估计的深度到边缘线索建模
MD2E: Modeling Depth-to-Edge Cues for Monocular Metric Depth Estimation
用预测边缘图的傅里叶频谱分位数作为度量尺度的代理，可在无相机内参时把相对深度校准成度量深度；边缘预测同时作为边界正则项，这一「深度→边缘」线索建模思路可迁移到其他需要尺度恢复的单目几何任务。
原文依据 we introduce a spectral quantile estimator (SQE) that analyzes the Fourier spectrum of a predicted edge map
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论本文研究在训练与推理阶段均不使用相机内参的单目度量深度估计（MMDE）。当焦距与场景深度同时变化时，图像中的深度变化难以被感知，但边缘频率统计会呈现出系统的、与尺度相关的偏移。基于这一观察，我们提出频谱分位数估计器（SQE），它分析预测边缘图的傅里叶频谱，并输出一个单一分数作为度量尺度的代理。由此，我们提出 MD2E 方法，通过对深度到边缘线索建模：从深度标注中导出边缘目标，利用频谱分数校准度量尺度，并在输出度量深度的同时用边缘预测对深度边界进行正则化。在多种相机与数据集上，MD2E 在零样本与微调两种设定下均取得单目度量深度估计的最优性能。项目主页见 https://2j472no.github.io/MD2E/。
英文原文摘要 939 字符
We study monocular metric depth estimation (MMDE) without camera intrinsics at training or inference. When focal length and scene depth vary together, depth changes are difficult to perceive in the image, yet the edge-frequency statistics exhibit systematic, scale-correlated shifts. Building on this observation, we introduce a spectral quantile estimator (SQE) that analyzes the Fourier spectrum of a predicted edge map and outputs a single score used as a proxy for metric scale. Consequently, we propose MD2E, a method that models depth-to-edge cues by deriving edge targets from depth annotations, calibrating metric scale using the spectral score, and using edge predictions to regularize depth boundaries while producing metric depth. Across diverse cameras and datasets, MD2E achieves state-of-the-art performance in MMDE in both zero-shot and fine-tuning settings. The project page is available at https://2j472no.github.io/MD2E/.