从频率与运动中看见深度：面向单目深度估计的渐进式训练范式
Seeing Depth Through Frequency and Motion: A Progressive Training Paradigm for Monocular Depth Estimation
可即插即用的频率引导采样模块（FGDepth）用于抑制频率混叠、锐化深度边界，以及用通道对齐注意力建模跨帧运动以提升位姿估计，这两点可直接迁移到其他自监督深度/位姿联合训练框架。
原文依据 FGDepth incorporates a plug-and-play Frequency-Guided Sampling module that explicitly enhances high-frequency details and suppresses aliasing artifacts
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论自监督单目深度估计近年来取得了显著进展，但频率混叠以及缺乏细粒度跨帧运动建模，仍然导致深度边界模糊和相机运动估计次优。为解决这些挑战，我们提出了一个渐进式自监督框架，集成了频率引导深度网络（FGDepth）与位姿查询网络（PQNet）。FGDepth 引入了一个即插即用的频率引导采样模块，显式增强高频细节并抑制混叠伪影，从而生成边界更锐利的深度图。PQNet 采用通道对齐注意力来建模细粒度的跨帧运动特征，从而实现更准确、更鲁棒的相机运动估计。此外，我们设计了一种渐进式三阶段解耦训练策略，有效利用了深度估计与位姿估计之间的互补性，进一步提升了整体性能。在 KITTI 基准上的大量实验表明其达到了最优性能，相较于强基线在 Sq Rel 上降低了 4.1%，并且我们的方法在 Make3D 上也展现出优异的跨数据集泛化能力。消融研究进一步验证了各提出组件的有效性。
英文原文摘要 1276 字符
Self-supervised monocular depth estimation has achieved remarkable progress in recent years, yet frequency aliasing and the lack of fine-grained cross-frame motion modeling still lead to blurred depth boundaries and suboptimal camera motion estimation.To address these challenges, we propose a progressive self-supervised framework that integrates a Frequency-Guided Depth Network (FGDepth) and a PoseQuery Network (PQNet). FGDepth incorporates a plug-and-play Frequency-Guided Sampling module that explicitly enhances high-frequency details and suppresses aliasing artifacts, producing depth maps with sharper boundaries. PQNet employs channel-aligned attention to model fine-grained cross-frame motion features, enabling more accurate and robust camera motion estimation. Furthermore, we design a progressive three-stage decoupled training strategy that effectively leverages the complementarity between depth and pose estimation, further improving overall performance.Extensive experiments on the KITTI benchmark demonstrate state-of-the-art performance, achieving a 4.1% reduction in Sq Rel over strong baselines, and our method also exhibits excellent cross-dataset generalization on Make3D. Ablation studies further validate the effectiveness of each proposed component.