Review on image-stitching techniques

Wang, Zhaobin; Yang, Zekun

doi:10.1007/s00530-020-00651-y

Cited by 79 publications

(39 citation statements)

References 81 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Seam removal is very important to improve the quality of the results, because humans are very sensitive to seams. There are three types of seam removal methods [43], namely pixel weighting [9,21], optimization [1,19], and transformation domain [3,29]. These methods can be regarded as post-processing, and we hope to solve this problem directly when training the end-to-end network.…”

Section: Related Workmentioning

confidence: 99%

An Adaptive Iterative Inpainting Method with More Information Exploration

Chen

Guo

Yuan

2021

Proceedings of the 29th ACM International Conference on Multimedia

View full text Add to dashboard Cite

The CNN-based image inpainting methods have achieved promising performance because of its outstanding semantic understanding and reasoning potentialities. However, previous works could not get satisfied results in some situations because information is not fully explored. In this paper, we propose a new method by combining three innovative ideas. First, to increase the diversity of the semantic information obtained by the network in image synthesis, we propose a multiple hidden space perceptual (MHSP) loss, which extracts high-level features from multiple pre-trained autoencoders. Second, we adopt an adaptive iterative reasoning (AIR) stategy to reduce the calculations under small-hole circumstances while ensuring the performance in large-hole circumstances. Third, we find that color inconsistencies occasionally occurred in the final image merging process, so we add a novel interval maximum saturation (IMS) loss to the final loss function. Experiments on the benchmark datasets show our method performs favorably against state-of-the-art approaches. Code is made publicly available at: https://github.com/IC-LAB/adaptive_iterative_inpainting. CCS CONCEPTS• Computing methodologies → Reconstruction.

show abstract

Section: Related Workmentioning

confidence: 99%

An Adaptive Iterative Inpainting Method with More Information Exploration

Chen

Guo

Yuan

2021

Proceedings of the 29th ACM International Conference on Multimedia

View full text Add to dashboard Cite

show abstract

“…Image stitching. [6][7][8][9][10][11][12][13] The early image stitching algorithm used a global homography transformation to align two images; however, the algorithms had strict imaging requirements regarding the two images. Both images must rotate around the same projection centre and capture a plane.…”

Section: Related Workmentioning

confidence: 99%

Semantic segmentation guided feature point classification and seam fusion for image stitching

Huang

Chen

Cheng

et al. 2021

Journal of Algorithms & Computational Technology

View full text Add to dashboard Cite

Image stitching can be employed to stitch images taken from different times, perspectives, or devices into a panorama with a wider view. However, the imaging specification of images to be stitched is strict. If the imaging specification is not satisfied, artefacts caused by inaccurate alignment and unnatural distortion will occur. Semantic segmentation can solve the classification problem at the pixel level; however, image stitching significantly depends on the accuracy of feature points. Therefore, this paper proposes an image stitching algorithm based on semantic segmentation to guide feature point classification and seam fusion. First, the images are recognized by a cascade semantic segmentation network, and the image feature points are classified. Thereafter, the corresponding homography transformations are calculated using different class feature points, and the best homography mapping for the entire target image is selected. Finally, a seam-cutting algorithm based on semantic segmentation is used to compute the seam, and a feathering Poisson fusion with distance transformation is used to eliminate artefacts and light differences. Experiments show that the algorithm can generate transitional natural and perceptual stitching results even under the influence of perspective and light differences.

show abstract

“…The image composition process computes the image gradients of both source and target images to generate a new desirable image of two composed images seamlessly. Other image processing that employs a similar approach includes image matting [1], image stitching [2], surface reconstruction [3], sharpening filter [4], image completion [5], and image inpainting [6]. In this paper, we present our work in using numerical methods to solve the image composition problem.…”

Section: Introductionmentioning

confidence: 99%

“…It was shown in their work that the proposed approach produced encouraging results for various natural images which previously were problematic. After that Wang and Yang [2] proposed an image stitching method to combines several images that have some overlapped images. A set of the cost function is defined where the similarity of the images and visibility of the seam were constructed in the gradient domain.…”

Section: Introductionmentioning

confidence: 99%

Modified iterative method with red-black ordering for image composition using poisson equation

Sunarto

2021

Bulletin EEI

View full text Add to dashboard Cite

Image composition involves the process of embedding a selected region of the source image to the target image to produce a new desirable image seamlessly. This paper presents an image composition procedure based on numerical differentiation using the laplacian operator to obtain the solution of the poisson equation. The proposed method employs the red-black strategy to speed up the computation by using two acceleration parameters. The method is known as modified two-parameter over-relaxation (MTOR) and is an extension of the existing relaxation methods. The MTOR was extensively studied in solving various linear equations, but its usefulness in image processing was never explored. Several examples were tested to examine the effectiveness of the proposed method in solving the poisson equation for image composition. The results showed that the proposed MTOR performed faster than the existing methods.

show abstract

Review on image-stitching techniques

Cited by 79 publications

References 81 publications

An Adaptive Iterative Inpainting Method with More Information Exploration

An Adaptive Iterative Inpainting Method with More Information Exploration

Semantic segmentation guided feature point classification and seam fusion for image stitching

Modified iterative method with red-black ordering for image composition using poisson equation

Contact Info

Product

Resources

About