Accurate Absolute Scale with Pseudo Depth Constraint for 3D Sparse Construction of Monocular RGB Image
- 16 April 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. PP (10518215) , 1
Abstract
3D Sparse reconstruction and camera pose estimation from monocular sequences are inherently plagued by scale ambiguity, which prevents the recovery of the scene’s absolute scale. Existing solutions are primarily limited in two aspects: (1) traditional geometric methods often depend on additional sensors or restrictive pre-calibration, lacking general applicability; (2) learning-based approaches frequently suffer from scale biases when faced with domain shifts. To overcome these challenges, this paper introduces a unified framework that deeply integrates monocular depth estimation into a traditional reconstruction pipeline. Our method leverages the robustness of modern depth prediction networks to eliminate cumbersome prior assumptions while employing iterative geometric refinement to ensure precise scale accuracy. The proposed framework begins by estimating depth maps via RGB images. First, an absolute scale factor is initialized from the depth priors to calibrate the initial two-view reconstruction, effectively aligning the model into a metric space. Second, during incremental reconstruction, new points and poses are registered via depth-constrained triangulation, with an iterative weighting strategy to enhance stability. Third, we propose a joint bundle adjustment that harmonizes reprojection and geometric errors using an adaptive Mahalanobis distance, which implicitly optimizes the global scale and refines the scene geometry concurrently. Comprehensive evaluations on the ETH3D, TUM-RGBD, and ICL-NUIM benchmarks demonstrate that our framework achieves state-of-the-art performance in absolute scale recovery. The results confirm that our method successfully maintains high geometric fidelity across diverse scenarios, proving its effectiveness and robustness.Keywords
Funding Information
- Beijing Natural Science Foundation (4252033)
- National Natural Science Foundation of China (62573036)
This publication has 62 references indexed in Scilit:
- Global Structure-from-Motion Revisited2024
- Resolving Scale Ambiguity in Multi-view 3D Reconstruction Using Dual-Pixel Sensors2024
- DeepSFM: Structure from Motion via Deep Bundle Adjustment2020
- Pixelwise View Selection for Unstructured Multi-View Stereo2016
- Robust Scale Estimation in Real-Time Monocular SFM for Autonomous Driving2014
- Accurate Scale Factor Estimation in 3D Reconstruction2013
- Bag‐of‐words‐driven, single‐camera simultaneous localization and mappingJournal of Field Robotics, 2010
- Multiple View Geometry in Computer Vision2004
- Multiple View Geometry in Computer VisionKybernetes, 2001
- Robust Estimation of a Location Parameter1992