Scholarlink

Purpose <p>In laparoscopic surgery, accurate 3D reconstruction from endoscopic video is crucial for effective image-guided techniques. Current methods for monocular depth estimation (MDE) face challenges in complex surgical scenes, including limited training data, specular reflections, and varying illumination conditions.</p> Methods <p>We propose SfMDiffusion, a novel diffusion-based self-supervised framework for MDE. Our approach combines: (1) a denoising diffusion process guided by pseudo-ground-truth depth maps, (2) knowledge distillation from a pre-trained teacher model, and (3) discriminative priors to enhance estimation robustness. Our design enables accurate depth estimation without requiring ground-truth depth data during training.</p> Results <p>Experiments on the SCARED and Hamlyn datasets demonstrate that SfMDiffusion achieves superior performance: an Absolute relative error (Abs Rel) of 0.049, a Squared relative error (Sq Rel) of 0.366, and a Root Mean Square Error (RMSE) of 4.305 on SCARED dataset, and Abs Rel of 0.067, Sq Rel of 0.800, and RMSE of 7.465 on Hamlyn dataset.</p> Conclusion <p>SfMDiffusion provides an innovative approach for 3D reconstruction in image-guided surgical techniques. Future work will focus on computational optimization and validation across diverse surgical scenarios. Our code is available at <a href="https://github.com/Skylanding/SfM-Diffusion">https://github.com/Skylanding/SfM-Diffusion</a>.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

SfMDiffusion: self-supervised monocular depth estimation in endoscopy based on diffusion models

  • 期刊论文

  • 发表日期：

    2025年2月24日

查看全文
  • Yu Li,
  • Da Chang,
  • Die Luo,
  • Jin Huang,
  • Lan Dong,
  • Du Wang,
  • Liye Mei,
  • Cheng Lei

摘要

Purpose

In laparoscopic surgery, accurate 3D reconstruction from endoscopic video is crucial for effective image-guided techniques. Current methods for monocular depth estimation (MDE) face challenges in complex surgical scenes, including limited training data, specular reflections, and varying illumination conditions.

Methods

We propose SfMDiffusion, a novel diffusion-based self-supervised framework for MDE. Our approach combines: (1) a denoising diffusion process guided by pseudo-ground-truth depth maps, (2) knowledge distillation from a pre-trained teacher model, and (3) discriminative priors to enhance estimation robustness. Our design enables accurate depth estimation without requiring ground-truth depth data during training.

Results

Experiments on the SCARED and Hamlyn datasets demonstrate that SfMDiffusion achieves superior performance: an Absolute relative error (Abs Rel) of 0.049, a Squared relative error (Sq Rel) of 0.366, and a Root Mean Square Error (RMSE) of 4.305 on SCARED dataset, and Abs Rel of 0.067, Sq Rel of 0.800, and RMSE of 7.465 on Hamlyn dataset.

Conclusion

SfMDiffusion provides an innovative approach for 3D reconstruction in image-guided surgical techniques. Future work will focus on computational optimization and validation across diverse surgical scenarios. Our code is available at https://github.com/Skylanding/SfM-Diffusion.