SMUDLP: Self-Teaching Multi-Frame Unsupervised Endoscopic Depth Estimation with Learnable Patchmatch

05/30/2022
by   Shuwei Shao, et al.
0

Unsupervised monocular trained depth estimation models make use of adjacent frames as a supervisory signal during the training phase. However, temporally correlated frames are also available at inference time for many clinical applications, e.g., surgical navigation. The vast majority of monocular systems do not exploit this valuable signal that could be deployed to enhance the depth estimates. Those that do, achieve only limited gains due to the unique challenges in endoscopic scenes, such as low and homogeneous textures and inter-frame brightness fluctuations. In this work, we present SMUDLP, a novel and unsupervised paradigm for multi-frame monocular endoscopic depth estimation. The SMUDLP integrates a learnable patchmatch module to adaptively increase the discriminative ability in low-texture and homogeneous-texture regions, and enforces cross-teaching and self-teaching consistencies to provide efficacious regularizations towards brightness fluctuations. Our detailed experiments on both SCARED and Hamlyn datasets indicate that the SMUDLP exceeds state-of-the-art competitors by a large margin, including those that use single or multiple frames at inference time. The source code and trained models will be publicly available upon the acceptance.

READ FULL TEXT

page 1

page 2

page 3

page 4

page 5

page 8

page 9

research
04/29/2021

The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth

Self-supervised monocular depth estimation networks are trained to predi...
research
12/27/2021

Improving Depth Estimation using Location Information

The ability to accurately estimate depth information is crucial for many...
research
04/25/2023

Exploring the Mutual Influence between Self-Supervised Single-Frame and Multi-Frame Depth Estimation

Although both self-supervised single-frame and multi-frame depth estimat...
research
03/26/2023

Multi-Frame Self-Supervised Depth Estimation with Multi-Scale Feature Fusion in Dynamic Scenes

Multi-frame methods improve monocular depth estimation over single-frame...
research
11/16/2021

NENet: Monocular Depth Estimation via Neural Ensembles

Depth estimation is getting a widespread popularity in the computer visi...
research
05/23/2022

MonoFormer: Towards Generalization of self-supervised monocular depth estimation with Transformers

Self-supervised monocular depth estimation has been widely studied recen...
research
08/18/2023

Robust Monocular Depth Estimation under Challenging Conditions

While state-of-the-art monocular depth estimation approaches achieve imp...

Please sign up or login with your details

Forgot password? Click here to reset