Published on Thu Mar 19 2020

Stereo Endoscopic Image Super-Resolution Using Disparity-Constrained Parallel Attention

Tianyi Zhang, Yun Gu, Xiaolin Huang, Enmei Tu, Jie Yang

The DCSSRnet provides a promising solution on enhancing spatial resolution of stereo image pairs, which will be extremely beneficial for the endoscopic surgery. Experiment results on laparoscopic images demonstrate that the proposed framework outperforms current SR methods.

0
0
0
Abstract

With the popularity of stereo cameras in computer assisted surgery techniques, a second viewpoint would provide additional information in surgery. However, how to effectively access and use stereo information for the super-resolution (SR) purpose is often a challenge. In this paper, we propose a disparity-constrained stereo super-resolution network (DCSSRnet) to simultaneously compute a super-resolved image in a stereo image pair. In particular, we incorporate a disparity-based constraint mechanism into the generation of SR images in a deep neural network framework with an additional atrous parallax-attention modules. Experiment results on laparoscopic images demonstrate that the proposed framework outperforms current SR methods on both quantitative and qualitative evaluations. Our DCSSRnet provides a promising solution on enhancing spatial resolution of stereo image pairs, which will be extremely beneficial for the endoscopic surgery.

Sun Nov 08 2020
Computer Vision
Real-time Surgical Environment Enhancement for Robot-Assisted Minimally Invasive Surgery Based on Super-Resolution
In Robot-Assisted Minimally Invasive Surgery (RAMIS), a camera assistant is typically required to control the position and zooming ratio of the laparoscope. We propose a multi-scale Generative Adversarial Network (GAN)-based video resolution method to construct a framework
0
0
0
Thu Mar 14 2019
Computer Vision
Learning Parallax Attention for Stereo Image Super-Resolution
Stereo image pairs can be used to improve the performance of super-resolution(SR) Since additional information is provided from a second viewpoint, it is challenging to incorporate this information for SR. We propose a parallax-attention stereo superresolution network to integrate the information.
0
0
0
Wed May 17 2017
Computer Vision
Self-Supervised Siamese Learning on Stereo Image Pairs for Depth Estimation in Robotic Surgery
Robotic surgery has become a powerful tool for performing minimally invasive procedures. Scene depth estimation is a prerequisite for AR, as accurate registration requires 3D correspondences between preoperative and intraoperative organ models. We propose a deep learning framework for surgical scene depth estimation.
0
0
0
Wed Sep 16 2020
Computer Vision
Parallax Attention for Unsupervised Stereo Correspondence Learning
Stereo image pairs encode 3D scene cues into stereo correspondences between left and right images. To exploit 3D cues within stereo images, recent CNN-based methods commonly use cost volume techniques to capture stereo correspondence over large disparities. The fixed maximum disparity used in cost volume methods hinders them
0
0
0
Tue Jun 18 2019
Computer Vision
Image Super Resolution via Bilinear Pooling: Application to Confocal Endomicroscopy
Miniaturized devices collect less light and have fewer optical components, resulting in pixelation artifacts and low resolution images. We propose a novel attention mechanism that combines 1st- and 2nd-order statistics for pooling operation, in both spatial and channel-wise dimensions.
0
0
0
Wed Jun 02 2021
Computer Vision
Feedback Network for Mutually Boosted Stereo Image Super-Resolution and Disparity Estimation
Under stereo settings, the problem of image super-resolution (SR) and disparity estimation are interrelated. We propose a Stereo Super-Resolution and Disparity Estimation Feedback Network (SSRDE-FNet) to handle both problems in a unified framework.
3
0
0