English

Depth Estimation from Single-shot Monocular Endoscope Image Using Image Domain Adaptation And Edge-Aware Depth Estimation

Image and Video Processing 2022-01-13 v1 Computer Vision and Pattern Recognition

Abstract

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.

Keywords

Cite

@article{arxiv.2201.04485,
  title  = {Depth Estimation from Single-shot Monocular Endoscope Image Using Image Domain Adaptation And Edge-Aware Depth Estimation},
  author = {Masahiro Oda and Hayato Itoh and Kiyohito Tanaka and Hirotsugu Takabatake and Masaki Mori and Hiroshi Natori and Kensaku Mori},
  journal= {arXiv preprint arXiv:2201.04485},
  year   = {2022}
}

Comments

Accepted paper as an oral presentation at Joint MICCAI workshop 2021, AE-CAI/CARE/OR2.0

R2 v1 2026-06-24T08:47:45.106Z