RISNet:无监督真实场景图像拼接网络

RISNet:unsupervised real scene image stitching network

图像拼接目的是获得一张高清无缝的全景图,现有方法依赖于特征匹配的准确性,会错误地对齐图像,产生伪影和失真等现象。为此提出一种新的无监督真实场景图像拼接网络,能够适应存在移动目标的真实场景拼接,保证全景图的精度无损失,包含配准和重建两个网络。在配准网络中引入内容感知分支,学习内容掩码,排除移动目标和误导性区域对于变换矩阵的负影响;在重建网络中添加边缘检测分支,构造边缘一致性感知损失,约束重建过程,优化图像细节,实现高清、无伪影的拼接效果。实验结果表明,该方法RMSE、PSNR、SSIM分别达到1.81、26.56、0.85,客观评价指标整体优于其他经典算法,用户调研结果也说明该方法获取的全景图清晰度更高。该方法有效地完成了真实场景下的无监督图像拼接,并能够泛化至其他场景的拼接任务中。

The purpose of image stitching is to obtain a high-definition,seamless panoramic image.Existing methods rely on the accuracy of feature matching,which will misalign images and produce errors such as artifacts and distortions.This paper proposed a new unsupervised real scene image stitching network which could adapt to real scene stitching in the presence of mo-ving targets and ensure no loss of accuracy in the panorama,including two networks of alignment and reconstruction.It excluded the negative influence of moving targets and misleading regions on the transformation matrix through content branching,and optimized image details by constraining the reconstruction process through edge branching to achieve high-definition and artifact-free stitching effects.The experimental results show that the method’s RMSE,PSNR,and SSIM reaches 1.81,26.56,and 0.85,respectively.The objective evaluation indexes are better than other classical algorithms overall,and the user research results also indicate that the method obtains higher definition of panoramic images.The method effectively accomplishes unsupervised image stitching in real scenes and can be generalized to stitching tasks in other scenes.