Abstract
Dense depth estimation from monocular video frames provides accurate intraoperative 3D point clouds for augmented reality surgical navigation. However, multi-frame depth estimation within the endoscopic scene suffers from the inaccurate matching of geometric relationships under subtle camera movements. To address this challenge, we propose a novel deep flow-to-depth method with uncertainty-driven recurrent refinement. Specifically, a pixel-wise uncertainty-driven optimizer is proposed to iteratively refine depth predictions instead of the traditional cost volume, effectively reducing depth errors caused by low textures and illumination variations. Furthermore, a two-view geometry with motion simulator is employed to augment the optical flow network’s ability to explore temporal correlations under subtle camera movements. Extensive cross-datasets experiments demonstrate the superior accuracy and generalization of our method, achieving RMSE values of 6.566 on C3VD, 7.972 on EndoSLAM, and 16.697 on ColonDepth datasets. Qualitative evaluation conducted on clinical dataset demonstrates the promising ability of our method to accurately estimate realistic anatomical structures in real-world scenarios. The code will be accessible at the following link: https://github. com/ILSR-SIA/Endo-DFD.
Funding Information
  • National Key Research and Development Program of China (2023YFB4705700)
  • National Natural Science Foundation of China (62303450)
  • National Natural Science Foundation of China (U20A20195)
  • Fundamental Research Project of Shenyang Institute of Automation (2023JC1K06)
  • Liaoning Province Science and Technology Project (2024JH2/102400049)
  • Liaoning Province Science and Technology Project (2025080132-JH2/1013)

This publication has 42 references indexed in Scilit: