Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
July 26, 2026˜The œinternational archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciencesOpen Access

Learning-based Monocular Depth Estimation for Photogrammetric 3D Reconstruction

View Full Paper
Ask AI
Bookmark
Share

Authors

CDChunyu DouNanjing Normal UniversityYYYifei YuWuhan UniversityXWXin WangWuhan University

Discussion

Loading...

Member takes

Implication

Randomized trial demonstrates improved geometric consistency in 3D reconstructions using monocular depth estimation.

Key Points

  • The study aims to enhance geometric consistency in monocular depth estimation for photogrammetric 3D reconstruction.
  • Utilized sparse point clouds from Structure-from-Motion as geometric constraints.
  • Developed a framework combining off-the-shelf learning-based MDE models without additional fine-tuning.
  • Implemented post-correction steps for depth map scaling based on SfM results.
  • Achieved improved geometric consistency in depth maps, enhancing reconstruction quality.
  • Demonstrated ability to predict globally consistent depth maps when SfM priors are available.
  • Identified key parameters influencing performance, including depth map resolution and voxel size.

Cite This Study

Dou et al. (2026) studied this question.

synapsesocial.com/papers/6a65a468d3aea3239cd77086https://doi.org/10.5194/isprs-archives-xlix-b2-2026-1345-2026
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. 1Multi-space Representation Fusion Enhanced Monocular Depth Estimation via Virtual Point Cloud2025
  2. 2Survey on Monocular Metric Depth Estimation2025
  3. 3Monocular Depth Estimation from UAV Images for 3D Documentation of Architectural Heritage: A Depth Anything V2-Based Approach2026
  4. 4SM4Depth: Seamless Monocular Metric Depth Estimation across Multiple Cameras and Scenes by One Model2024
  5. 5MonoViT-3D: Self-Supervised Monocular Depth Estimation from 3D Geometric Constraints using Point Cloud Projection2024