用稀疏3D数据将相对深度转为度量深度，提升精度与效率。
The Midas Touch for Metric Depth
- 通过稀疏图优化分段恢复，再用几何代价逐像素精修
- 在多个数据集上显著优于现有深度补全与估计方法
- 轻量可插拔，适合各类下游3D任务部署
近期进展显著提升了相对深度估计的跨场景泛化能力，但其实际应用仍受限于缺乏度量尺度、局部尺度不一致及计算效率低。为此，我们提出数学可解释的「Midas Touch for Depth」（MTD）方法，仅需极稀疏的3D数据即可将相对深度转换为度量深度。为消除局部尺度不一致，采用基于稀疏图优化的分段恢复策略，再结合不连续感知的测地线代价进行像素级精修。MTD展现出强泛化能力，在多个基准测试中显著优于先前的深度补全与深度估计方法。此外，其轻量化、可插拔的设计便于在多样下游3D任务中部署与集成。项目页面见 https://mias.group/MTD。
原文摘要 · Abstract (English)
Recent advances have markedly improved the cross-scene generalization of relative depth estimation, yet its practical applicability remains limited by the absence of metric scale, local inconsistencies, and low computational efficiency. To address these issues, we present \emph{\textbf{M}idas \textbf{T}ouch for \textbf{D}epth} (MTD), a mathematically interpretable approach that converts relative depth into metric depth using only extremely sparse 3D data. To eliminate local scale inconsistencies, it applies a segment-wise recovery strategy via sparse graph optimization, followed by a pixel-wise refinement strategy using a discontinuity-aware geodesic cost. MTD exhibits strong generalization and achieves substantial accuracy improvements over previous depth completion and depth estimation methods. Moreover, its lightweight, plug-and-play design facilitates deployment and integration on diverse downstream 3D tasks. Project page is available at https://mias.group/MTD.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。