Depth Estimation from Single-shot Monocular Endoscope Image Using Image Domain Adaptation And Edge-Aware Depth Estimation
Not on the map. Why?
Abstract (arXiv)
We propose a depth estimation method from a single-shot monocular endoscopic image using Lambertian surface translation by domain adaptation and depth estimation using multi-scale edge loss. We employ a two-step estimation process including Lambertian surface translation from unpaired data and depth estimation. The texture and specular reflection on the surface of an organ reduce the accuracy of depth estimations. We apply Lambertian surface translation to an endoscopic image to remove these texture and reflections. Then, we estimate the depth by using a fully convolutional network (FCN). During the training of the FCN, improvement of the object edge similarity between an estimated image and a ground truth depth image is important for getting better results. We introduced a muti-scale edge loss function to improve the accuracy of depth estimation. We quantitatively evaluated the proposed method using real colonoscopic images. The estimated depth values were proportional to the real depth values. Furthermore, we applied the estimated depth images to automated anatomical location identification of colonoscopic images using a convolutional neural network. The identification accuracy of the network improved from 69.2% to 74.1% by using the estimated depth images.
Key facts. Cited by 1 paper in the map (data through 13 Oct 2026). Builds on 20 of its 34 references that are in the map. First posted on arXiv 12 Jan 2022.
Builds on
20 of 34 references.
References · 20
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,656
- 2016Densely Connected Convolutional Networkscited by 6,707
- 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,193
- 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
- 2016Deeper Depth Prediction with Fully Convolutional Residual Networkscited by 403
- 2016EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic Videoscited by 366
- 2019GA-Net: Guided Aggregation Net for End-to-end Stereo Matchingcited by 244
- 2019Group-wise Correlation Stereo Networkcited by 235
- 2018High Quality Monocular Depth Estimation via Transfer Learningcited by 133
- 2019Neural RGB->D Sensing: Depth and Uncertainty from a Video Cameracited by 69
- 2017Unsupervised Reverse Domain Adaptation for Synthetic Medical Images via Adversarial Trainingcited by 57
- 2019Deep Rigid Instance Scene Flowcited by 54
8 more
- 2019Dense Depth Estimation in Monocular Endoscopy with Self-supervised Learning Methodscited by 46
- 2018Single View Stereo Matchingcited by 39
- 2017Deep Learning and Conditional Random Fields-based Depth Estimation and Topographical Reconstruction from Conventional Endoscopycited by 31
- 2019StereoDRNet: Dilated Residual Stereo Netcited by 29
- 2019Deep Robust Single Image Depth Estimation Neural Network Using Scene Understandingcited by 15
- 2018Self-supervised Learning for Dense Depth Estimation in Monocular Endoscopycited by 13
- 2018Deep Learning with Cinematic Rendering: Fine-Tuning Deep Neural Networks Using Photorealistic Medical Imagescited by 10
- 2018SfMLearner++: Learning Monocular Depth & Ego-Motion using Meaningful Geometric Constraintscited by 1
Built on by
Citing papers per year: 2024: 1.
1 paper.