# Self-supervised Learning for Dense Depth Estimation in Monocular Endoscopy

arXiv: https://arxiv.org/abs/1806.09521 · HTML: https://mlsanity.com/paper/1806.09521/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jun 2018.

## Built on by (most cited first, 13 of 13)

- [Stereo Correspondence and Reconstruction of Endoscopic Data Challenge](https://mlsanity.com/paper/2101.01133/) (2021)
- [ContIG: Self-supervised Multimodal Contrastive Learning for Medical Imaging with Genetics](https://mlsanity.com/paper/2111.13424/) (2021)
- [Tracking and Mapping in Medical Computer Vision: A Review](https://mlsanity.com/paper/2310.11475/) (2023)
- [An Evaluation of Self-Supervised Pre-Training for Skin-Lesion Analysis](https://mlsanity.com/paper/2106.09229/) (2021)
- [GRIN: Zero-Shot Metric Depth with Pixel-Level Diffusion](https://mlsanity.com/paper/2409.09896/) (2024)
- [3D endoscopic depth estimation using 3D surface-aware constraints](https://mlsanity.com/paper/2203.02131/) (2022)
- [3D Semantic Mapping from Arthroscopy using Out-of-distribution Pose and Depth and In-distribution Segmentation Training](https://mlsanity.com/paper/2106.05525/) (2021)
- [Depth Estimation from Single-shot Monocular Endoscope Image Using Image Domain Adaptation And Edge-Aware Depth Estimation](https://mlsanity.com/paper/2201.04485/) (2022)
- [Benchmarking Robustness of Endoscopic Depth Estimation with Synthetically Corrupted Data](https://mlsanity.com/paper/2409.16063/) (2024)
- [Geo-RepNet: Geometry-Aware Representation Learning for Surgical Phase Recognition in Endoscopic Submucosal Dissection](https://mlsanity.com/paper/2507.09294/) (2025)
- [Endoscopic Depth Estimation Based on Deep Learning: A Survey](https://mlsanity.com/paper/2507.20881/) (2025)
- [Stereo Video Reconstruction Without Explicit Depth Maps for Endoscopic Surgery](https://mlsanity.com/paper/2109.08227/) (2021)
- [Multi-Modal Monocular Endoscopic Depth and Pose Estimation with Edge-Guided Self-Supervision](https://mlsanity.com/paper/2602.17785/) (2026)

## Abstract (arXiv)

We present a self-supervised approach to training convolutional neural networks for dense depth estimation from monocular endoscopy data without a priori modeling of anatomy or shading. Our method only requires sequential data from monocular endoscopic videos and a multi-view stereo reconstruction method, e.g. structure from motion, that supervises learning in a sparse but accurate manner. Consequently, our method requires neither manual interaction, such as scaling or labeling, nor patient CT in the training and application phases. We demonstrate the performance of our method on sinus endoscopy data from two patients and validate depth prediction quantitatively using corresponding patient CT scans where we found submillimeter residual errors.