A Stronger Stitching Algorithm for Fisheye Images based on Deblurring and Registration

TL;DR

This paper introduces a novel fisheye image stitching approach combining a deep learning-based deblurring network and an improved registration algorithm, resulting in higher quality panoramic images.

Contribution

It presents ANAFNet for effective fisheye image deblurring and OFG for enhanced image registration, advancing fisheye image stitching techniques.

Findings

ANAFNet effectively restores sharp images from blurred fisheye inputs.

OFG improves registration accuracy over traditional methods.

The combined approach yields higher quality panoramic images.

Abstract

Fisheye lens, which is suitable for panoramic imaging, has the prominent advantage of a large field of view and low cost. However, the fisheye image has a severe geometric distortion which may interfere with the stage of image registration and stitching. Aiming to resolve this drawback, we devise a stronger stitching algorithm for fisheye images by combining the traditional image processing method with deep learning. In the stage of fisheye image correction, we propose the Attention-based Nonlinear Activation Free Network (ANAFNet) to deblur fisheye images corrected by Zhang calibration method. Specifically, ANAFNet adopts the classical single-stage U-shaped architecture based on convolutional neural networks with soft-attention technique and it can restore a sharp image from a blurred image effectively. In the part of image registration, we propose the ORB-FREAK-GMS (OFG), a comprehensive image matching algorithm, to improve the accuracy of image registration. Experimental results demonstrate that panoramic images of superior quality stitching by fisheye images can be obtained through our method.