# Occlusion-Aware Self-Supervised Monocular Depth Estimation for Weak-Texture Endoscopic Images

arXiv: https://arxiv.org/abs/2504.17582 · HTML: https://mlsanity.com/paper/2504.17582/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 17 references that are in the map.
- First posted on arXiv 24 Apr 2025.

## Builds on (most cited first, 8 of 8)

- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Unsupervised Learning of Depth and Ego-Motion from Video](https://mlsanity.com/paper/1704.07813/) (2017)
- [Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation](https://mlsanity.com/paper/1904.05290/) (2019)
- [Self-Supervised Monocular Depth and Ego-Motion Estimation in Endoscopy: Appearance Flow to the Rescue](https://mlsanity.com/paper/2112.08122/) (2021)
- [Deep Feature Factorization For Concept Discovery](https://mlsanity.com/paper/1806.10206/) (2018)
- [DeFeat-Net: General Monocular Depth via Simultaneous Unsupervised Representation Learning](https://mlsanity.com/paper/2003.13446/) (2020)
- [Endoscopic navigation in the absence of CT imaging](https://mlsanity.com/paper/1806.03997/) (2018)
- [EndoDepth: A Benchmark for Assessing Robustness in Endoscopic Depth Prediction](https://mlsanity.com/paper/2409.19930/) (2024)

## Built on by (most cited first, 1 of 1)

- [Multi-Modal Monocular Endoscopic Depth and Pose Estimation with Edge-Guided Self-Supervision](https://mlsanity.com/paper/2602.17785/) (2026)

## Abstract (arXiv)

We propose a self-supervised monocular depth estimation network tailored for endoscopic scenes, aiming to infer depth within the gastrointestinal tract from monocular images. Existing methods, though accurate, typically assume consistent illumination, which is often violated due to dynamic lighting and occlusions caused by GI motility. These variations lead to incorrect geometric interpretations and unreliable self-supervised signals, degrading depth reconstruction quality. To address this, we introduce an occlusion-aware self-supervised framework. First, we incorporate an occlusion mask for data augmentation, generating pseudo-labels by simulating viewpoint-dependent occlusion scenarios. This enhances the model's ability to learn robust depth features under partial visibility. Second, we leverage semantic segmentation guided by non-negative matrix factorization, clustering convolutional activations to generate pseudo-labels in texture-deprived regions, thereby improving segmentation accuracy and mitigating information loss from lighting changes. Experimental results on the SCARED dataset show that our method achieves state-of-the-art performance in self-supervised depth estimation. Additionally, evaluations on the Endo-SLAM and SERV-CT datasets demonstrate strong generalization across diverse endoscopic environments.