# Bayesian dense inverse searching algorithm for real-time stereo matching in minimally invasive surgery

arXiv: https://arxiv.org/abs/2106.07136 · HTML: https://mlsanity.com/paper/2106.07136/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 37 references that are in the map.
- First posted on arXiv 14 Jun 2021.

## Builds on (most cited first, 16 of 16)

- [Pyramid Stereo Matching Network](https://mlsanity.com/paper/1803.08669/) (2018)
- [Direct Sparse Odometry](https://mlsanity.com/paper/1607.02565/) (2016)
- [Group-wise Correlation Stereo Network](https://mlsanity.com/paper/1903.04025/) (2019)
- [Hierarchical Deep Stereo Matching on High-resolution Images](https://mlsanity.com/paper/1912.06704/) (2019)
- [Stereo Correspondence and Reconstruction of Endoscopic Data Challenge](https://mlsanity.com/paper/2101.01133/) (2021)
- [Fast Optical Flow using Dense Inverse Search](https://mlsanity.com/paper/1603.03590/) (2016)
- [T2Net: Synthetic-to-Realistic Translation for Solving Single-Image Depth Estimation Tasks](https://mlsanity.com/paper/1808.01454/) (2018)
- [Self-Supervised Siamese Learning on Stereo Image Pairs for Depth Estimation in Robotic Surgery](https://mlsanity.com/paper/1705.08260/) (2017)
- [MIS-SLAM: Real-time Large Scale Dense Deformable SLAM System in Minimal Invasive Surgery Based on Heterogeneous Computing](https://mlsanity.com/paper/1803.02009/) (2018)
- [Dynamic Reconstruction of Deformable Soft-tissue with Stereo Scope in Minimal Invasive Surgery](https://mlsanity.com/paper/2003.10867/) (2020)
- [S2R-DepthNet: Learning a Generalizable Depth-specific Structural Representation](https://mlsanity.com/paper/2104.00877/) (2021)
- [Deep EndoVO: A Recurrent Convolutional Neural Network (RCNN) based Visual Odometry Approach for Endoscopic Capsule Robots](https://mlsanity.com/paper/1708.06822/) (2017)
- [3D Reconstruction of Whole Stomach from Endoscope Video Using Structure-from-Motion](https://mlsanity.com/paper/1905.12988/) (2019)
- [Autonomous Tissue Scanning under Free-Form Motion for Intraoperative Tissue Characterisation](https://mlsanity.com/paper/2005.05050/) (2020)
- [Autonomous Scanning for Endomicroscopic Mosaicing and 3D Fusion](https://mlsanity.com/paper/1604.04137/) (2016)
- [Combining Deep Learning with Geometric Features for Image based Localization in the Gastrointestinal Tract](https://mlsanity.com/paper/2005.05481/) (2020)

## Built on by (most cited first, 3 of 3)

- [BDIS: Bayesian Dense Inverse Searching Method for Real-Time Stereo Surgical Image Matching](https://mlsanity.com/paper/2205.03133/) (2022)
- [BDIS-SLAM: A lightweight CPU-based dense stereo SLAM for surgery](https://mlsanity.com/paper/2312.15679/) (2023)
- [A Disparity Refinement Framework for Learning-based Stereo Matching Methods in Cross-domain Setting for Laparoscopic Images](https://mlsanity.com/paper/2302.02294/) (2023)

## Abstract (arXiv)

This paper reports a CPU-level real-time stereo matching method for surgical images (10 Hz on 640 * 480 image with a single core of i5-9400). The proposed method is built on the fast ''dense inverse searching'' algorithm, which estimates the disparity of the stereo images. The overlapping image patches (arbitrary squared image segment) from the images at different scales are aligned based on the photometric consistency presumption. We propose a Bayesian framework to evaluate the probability of the optimized patch disparity at different scales. Moreover, we introduce a spatial Gaussian mixed probability distribution to address the pixel-wise probability within the patch. In-vivo and synthetic experiments show that our method can handle ambiguities resulted from the textureless surfaces and the photometric inconsistency caused by the Lambertian reflectance. Our Bayesian method correctly balances the probability of the patch for stereo images at different scales. Experiments indicate that the estimated depth has higher accuracy and fewer outliers than the baseline methods in the surgical scenario.