小秋在路上~

在图像拼接的合成步骤中，特别是对于具有视差的图像，接缝切割方法已经被证明是有效的。然而，接缝切割的有效性通常依赖于图像的粗略对齐，使得图像中存在一个局部区域，在该区域内可以找到看似合理的接缝，对于视差较大的图像，现有的对齐方法往往达不到预期的效果。本文提出了一种以接缝质量评价为指导的局部对齐和拼接方法. 首先，利用现有的图像对齐和接缝分割方法计算出初始接缝，并对接缝处的像素质量进行评价。然后，对于低质量的像素，在对齐图像中分离其封闭块，并通过SIFT流提取修改的稠密对应来局部对齐它们。

Yu, J., Yu, Y., & Da, F. (2023). Parallax-Tolerant Image Stitching with Epipolar Displacement Field. arXiv preprint arXiv:2311.16637.

Yu J, Yu Y, Da F. Parallax-Tolerant Image Stitching with Epipolar Displacement Field[J]. arXiv preprint arXiv:2311.16637, 2023.

Liu Y B, Qin J H, Zhu M Y, et al. Fast stitching method for multi-view images of cupping spots[J]. Signal, Image and Video Processing, 2023, 17(5): 1905-1913.

Zhang J, Xiu Y. Image stitching based on human visual system and SIFT algorithm[J]. The Visual Computer, 2023: 1-13.

作者单位DOI。

Zhang L, Huang H. Image stitching with manifold optimization[J]. IEEE Transactions on Multimedia, 2022.

Chen Y, Zheng H, Ma Y, et al. Image stitching based on angle-consistent warping[J]. Pattern Recognition, 2021, 117: 107993.

Zhang Z, Yang X, Xu C. Natural image stitching with layered warping constraint[J]. IEEE Transactions on Multimedia, 2021.

Jia Q, Li Z J, Fan X, et al. Leveraging line-point consistence to preserve structures for wide parallax image stitching[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2021: 12186-12195.

Yuan X, Zheng Y, Zhao W, et al. Image stitching method by multi‐feature constrained alignment and colour adjustment[J]. IET Image Processing, 2021, 15(7): 1499-1507.

Xue W, Xie W, Zhang Y, et al. Stable linear structures and seam measurements for parallax image stitching[J]. IEEE transactions on circuits and systems for video technology, 2021, 32(1): 253-261.

Pellikka M, Lahtinen V. A robust method for image stitching[J]. Pattern Analysis and Applications, 2021, 24(4): 1847-1858.

DOI。

Madhusudana P C, Soundararajan R. Subjective and objective quality assessment of stitched images for virtual reality[J]. IEEE Transactions on Image Processing, 2019, 28(11): 5620-5635.

DOI: 10.1109/TIP.2019.2949424

Lin L, Ding Y, Wang L, et al. Line-preserving video stitching for asymmetric cameras[J]. Multimedia Tools and Applications, 2019, 78: 14591-14611.

Liao T, Li N. Single-perspective warps in natural image stitching[J]. IEEE transactions on image processing, 2019, 29: 724-735.

Qiu S, Zhou D, Du Y. The image stitching algorithm based on aggregated star groups[J]. Signal, Image and Video Processing, 2019, 13: 227-235.

Zheng J, Wang Y, Wang H, et al. A novel projective-consistent plane based image stitching method[J]. IEEE Transactions on Multimedia, 2019, 21(10): 2561-2575.

近年来，图像拼接发展迅速。接缝消除在图像拼接中起着关键作用。因此，本文提出了一种改进的图像拼接缝消除方法。首先，注册图像。然后，提出了基于Curvelet变换的最优焊缝方法来消除煤层。客观评价指标（PSNR和SSIM）用于评价实验结果中所提方法的性能。本文还提出了一种评估拼接图像局部质量的新指标。在该度量下测试三组图像。实验结果表明，该方法可以有效地消除煤层。Curvelet是一种用于多尺度物体表示的非自适应技术，于1999年提出并在2002年进行了改进（Candes和Guo，2002）。

参考文献Jacob G M, Das S. GreenWarps: A Two-Stage Warping Model for Stitching Images Using Diffeomorphic Meshes and Green Coordinates[C]//European Conference on Computer Vision. Springer, Cham, 2018: 74...

参考文献：Li J, Wang Z, Lai S, et al. Parallax-Tolerant Image Stitching Based on Robust Elastic Warping[J]. IEEE Transactions on Multimedia, 2018, 20(7).截至2018年9月6日，该论文在Google学术上的引用量为1.大类学科 小类学科 ...

视频拼接在计算机视觉中仍然是一个具有挑战性的问题，特别是对于移动物体周围广泛存在的伪像，包括视差，鬼影等。传统方法通常依赖于单个投影模型，这可能导致重叠区域中移动物体的不准确对应。在本文中，我们利用重叠区域中的光流场。

Hejazifar H, Khotanlou H. Fast and robust seam estimation to seamless image stitching[J]. Signal, Image and Video Processing, 2018, 12: 885-893.

Xu B, Jia Y. Wide-angle image stitching using multi-homography warping[C]//2017 IEEE International Conference on Image Processing (ICIP). IEEE, 2017: 1467-1471.

该作是武汉大学出品。关注的角度与之前的不一样。主要关注重叠区域的颜色过渡。

Li C, Liu Z Y, Yang X, et al. Stitching contaminated images[J]. Neurocomputing, 2016, 214: 829-836.

Yung-Yu Chuang大神组出品的大作。

参考文献：Lin K, Jiang N, Cheong L F, et al. Seagull: seam-guided local alignment for parallax-tolerant image stitching[C]//European Conference on Computer Vision. Springer, Cham, 2016: 370-385.截至2018年...

Lin C C, Pankanti S U, Natesan Ramamurthy K, et al. Adaptive as-natural-as-possible image stitching[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015: 1155-1163.

Zhang F, Liu F. Parallax-tolerant image stitching[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2014: 3262-3269.

Chang C H, Sato Y, Chuang Y Y. Shape-preserving half-projective warps for image stitching[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2014: 3254-3261.

Zaragoza J, Chin T J, Brown M S, et al. As-projective-as-possible image stitching with moving DLT[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2013: 2339-2346.

He K, Chang H, Sun J. Rectangling panoramic images via warping[J]. ACM Transactions on Graphics (TOG), 2013, 32(4): 1-10.

很多文章都是根据该篇论文的idea处理视差。这篇文章得好好读一下才行。

Brown M, Lowe D G. Automatic panoramic image stitching using invariant features[J]. International journal of computer vision, 2007, 74: 59-73.

1、低纹理（low-texture）2、大视差（large parallax）3、宽基线（wide-baseline）