Skip to main navigation Skip to search Skip to main content

Hybrid Feature Edge Enhancement for Self-Supervised Monocular Depth Estimation in Endoscopic Scenes

  • Jiadong Guo
  • , Ke Niu*
  • , Xue Feng
  • , Heng Li*
  • , Mingyang Ou
  • , Zeyun Liu
  • *Corresponding author for this work
  • Beijing Information Science & Technology University
  • Southern University of Science and Technology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Reliable monocular depth prediction from endoscopic video frames remains useful for scale-aware scene understanding during minimally invasive procedures and supports applications including surgical 3D reconstruction and intraoperative navigation guidance. However, self-supervised methods based on photometric reconstruction often become unstable in weakly textured tissue regions and near poorly separated tissue interfaces, which may cause blurred depth transitions and distorted local geometry. To mitigate these limitations, we design a boundary-oriented self-supervised endoscopic depth model with hybrid edge-feature enhancement. The proposed model improves boundary detail preservation and local structural consistency by strengthening tissue-boundary-sensitive representations and enhancing cross-scale decoder fusion. Specifically, it consists of a Hybrid Feature Edge Enhancement Module (HFE-EM) and a Multi-Feature Fusion Convolutional Block (MFCB). HFE-EM incorporates complementary edge and texture cues into encoder features to improve boundary-aware representation learning, while MFCB refines decoder-side feature aggregation under global contextual guidance. Experiments on the SCARED dataset, cross-dataset evaluation using Hamlyn, and ablation studies show that our method obtains competitive performance and good generalization ability for depth estimation in endoscopic scenes.

Original languageEnglish
Title of host publicationAdvanced Intelligent Computing Technology and Applications - 22nd International Conference on Intelligent Computing, ICIC 2026, Proceedings
EditorsDe-Shuang Huang, Qinhu Zhang, Yijie Pan, Chuanlei Zhang, Wei Chen, Bo Li, Wenzheng Bao, Prashan Premaratne
PublisherSpringer Science and Business Media Deutschland GmbH
Pages164-175
Number of pages12
ISBN (Print)9789819235124
DOIs
Publication statusPublished - 2027
Externally publishedYes
Event22nd International Conference on Intelligent Computing, ICIC 2026 - Toronto, Canada
Duration: 22 Jul 202626 Jul 2026

Publication series

NameLecture Notes in Computer Science
Volume16662 LNCS
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference22nd International Conference on Intelligent Computing, ICIC 2026
Country/TerritoryCanada
CityToronto
Period22/07/2626/07/26

Keywords

  • Boundary-aware representation
  • Label-free monocular depth prediction
  • Surgical endoscopy
  • Texture enhancement

Fingerprint

Dive into the research topics of 'Hybrid Feature Edge Enhancement for Self-Supervised Monocular Depth Estimation in Endoscopic Scenes'. Together they form a unique fingerprint.

Cite this