The Hamlyn Symposium on Medical Robotics 2022: 26th-29th June 2022
  • Home
  • Programme
  • Keynotes
  • Workshops
  • Industry Forum
  • Funders’ Forum
  • Registration
  • Home
    • About
    • Ethical MedTech Compliance
    • Proceedings
    • IEEE T-MRB Journal
  • Programme
    • Programme Committee
    • Keynotes
    • Industry Forum
    • Funders’ Forum
    • Workshops
    • Sponsor-Led Events
  • Fees & Registration
  • Sponsors & Exhibitors
  • Surgical Robot Challenge
  • Contact
Get involved

Self-supervised Monocular Depth Estimation with 3DD Module in Laparoscopic Images for Robotic Surgery

Self-supervised monocular depth estimation (SMDE) is a deep learning algorithm that takes reconstructed images as supervisory signal and generates loss to train the depth estimation model by backpropagation. SMDE has achieved remarkable performance in the autonomous driving field, which utilizes ego-motion matrix to build the relation between frames (show in Fig. 1) [1-3].

To enhance 3D perception of surgeons in minimally invasive surgery (MIS), it is essential to generate precise depth map from laparoscopic images. Different from autonomous driving scene, the training framework is established under the assumption that the position of the camera is static, and objects are dynamic (moving surgical instruments and deformable tissues). Therefore, the ego-motion model is replaced by the 3D displacement (3DD) module.

View poster
Share this page

Stay in touch

Sign up to our newsletter to be the first to hear about exciting events, opportunities and news.
  • This field is for validation purposes and should be left unchanged.

The information you supply will be processed in line with our privacy notice.

The Hamlyn Symposium
on Medical Robotics
Imperial College London
  • Programme
  • Showcase
  • Challenges
  • Accessibility
  • Press
  • Privacy
© 2021 Imperial College London