Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
November 20, 2025ComputersOpen Access

Survey on Monocular Metric Depth Estimation

View Full Paper
Ask AI
Bookmark
Share

Authors

JZJiuling ZhangYWYurong WuHJHuilong Jiang

Discussion

Loading...

Member takes

Implication

This survey reveals advancements in monocular metric depth estimation for spatial understanding and accurate 3D modeling, highlighting key datasets and methodologies.

Key Points

  • Monocular metric depth estimation generates accurate depth maps from RGB images, enhancing spatial understanding and navigation.
  • Key datasets like KITTI and NYU-Depth provide absolute ground-truth depth essential for advancing depth estimation techniques.
  • Observational analysis highlights recent methodological progress in model architecture, domain generalization, and loss design for improved depth estimation.
  • This work outlines open challenges in metric depth estimation, emphasizing its necessity for robust real-world vision systems.

Cite This Study

Zhang et al. (2025) studied this question.

synapsesocial.com/papers/6924f074c0ce034ddc34fbd5https://doi.org/10.3390/computers14110502
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1SM4Depth: Seamless Monocular Metric Depth Estimation across Multiple Cameras and Scenes by One Model2024
  2. 2UniDepth: Universal Monocular Metric Depth Estimation2024 · 3 citations
  3. 3Learning-based Monocular Depth Estimation for Photogrammetric 3D Reconstruction2026
  4. 4ScaleDepth: Decomposing Metric Depth Estimation Into Semantic-Aware Scale Prediction and Adaptive Relative Depth Estimation2026 · 4 citations
  5. 5Metric3D v2: A Versatile Monocular Geometric Foundation Model for Zero-Shot Metric Depth and Surface Normal Estimation2024 · 12 citations