A Disparity Refinement Framework for Learning-based Stereo Matching Methods in Cross-domain Setting for Laparoscopic Images

TL;DR

This paper introduces a disparity refinement framework to enhance the robustness and accuracy of learning-based stereo matching methods in cross-domain laparoscopic image depth estimation, addressing domain shift challenges.

Contribution

The paper proposes a novel disparity refinement framework combining local and global methods to improve stereo matching in cross-domain laparoscopic images, even with limited training data.

Findings

Effective refinement of disparity maps on unseen datasets

Improved robustness without sacrificing accuracy

Framework enhances existing learning-based stereo matching methods

Abstract

Purpose: Stereo matching methods that enable depth estimation are crucial for visualization enhancement applications in computer-assisted surgery (CAS). Learning-based stereo matching methods are promising to predict accurate results on laparoscopic images. However, they require a large amount of training data, and their performance may be degraded due to domain shifts. Methods: Maintaining robustness and improving the accuracy of learning-based methods are still open problems. To overcome the limitations of learning-based methods, we propose a disparity refinement framework consisting of a local disparity refinement method and a global disparity refinement method to improve the results of learning-based stereo matching methods in a cross-domain setting. Those learning-based stereo matching methods are pre-trained on a large public dataset of natural images and are tested on two datasets of laparoscopic images. Results: Qualitative and quantitative results suggest that our proposed disparity framework can effectively refine disparity maps when they are noise-corrupted on an unseen dataset, without compromising prediction accuracy when the network can generalize well on an unseen dataset. Conclusion: Our proposed disparity refinement framework could work with learning-based methods to achieve robust and accurate disparity prediction. Yet, as a large laparoscopic dataset for training learning-based methods does not exist and the generalization ability of networks remains to be improved, the incorporation of the proposed disparity refinement framework into existing networks will contribute to improving their overall accuracy and robustness associated with depth estimation.