Natural Image Stitching with the Global Similarity Prior

Chen, Yu-Sheng; Chuang, Yung-Yu

doi:10.1007/978-3-319-46454-1_12

Cited by 177 publications

(192 citation statements)

References 16 publications

Supporting

Mentioning

192

Contrasting

Order By: Relevance

“…5 gives comparison with state-of-the-art methods in terms of line preserving. In [4], the line segment detection is used for feature preserving in global transformation, like scale…”

Section: Results and Applicationsmentioning

confidence: 99%

“…Comparison with image completion. (a) initial stitching result by [4], (b) our piecewise rectangling panorama, (c) image completion result by [30] applied to (a), (d) image completion result by applying [30] to our stitching result in (b).…”

Section: A Results and Comparisonsmentioning

confidence: 99%

“…The warped meshes of the stitched images with irregular boundaries will serve as an initial values for the optimization to get piecewise rectangular stitching result. Inspired by [4], we stitch images using the global similarity prior to generate more natural panoramas without too much distortion or limited field of view. Like previous methods, image stitching is performed by meshbased image warping on input images.…”

Section: Initial Image Stitchingmentioning

confidence: 99%

“…For any other image I i (2 ≤ i ≤ N ), the desired scaling s i and rotation angle θ i w.r.t. I 1 are calculated according to [4]. The global similarity term is defined as…”

Section: Initial Image Stitchingmentioning

confidence: 99%

“…8 for some examples). After stitching input images using a traditional method with the global similarity prior [4], we extract the outer boundary of the stitching result and analyze the boundary constraints, and finally perform a global optimization taking these constraints into account to obtain the stitching result with a piecewise rectangular boundary. Our method can robustly stitch a large number of images.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Content-Preserving Image Stitching With Piecewise Rectangular Boundary Constraints

Yun

Lai

Zhang

2021

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

This paper proposes an approach to contentpreserving image stitching with regular boundary constraints, which aims to stitch multiple images to generate a panoramic image with regular boundary. Existing methods treat image stitching and rectangling as two separate steps, which may result in suboptimal results as the stitching process is not aware of the further warping needs for rectangling. We address these limitations by formulating image stitching with regular boundaries in a unified optimization. Starting from the initial stitching results produced by traditional warping-based optimization, we obtain the irregular boundary from the warped meshes by polygon Boolean operations which robustly handle arbitrary mesh compositions, and by analyzing the irregular boundary construct a piecewise rectangular boundary. Based on this, we further incorporate straight line preserving and regular boundary constraints into the image stitching framework, and conduct iterative optimization to obtain an optimal piecewise rectangular boundary, thus can make the boundary of stitching results as close as possible to a rectangle, while reducing unwanted distortions. We further extend our method to selfie expansion and video stitching, by integrating the portrait preservation and temporal coherence into the optimization. Experiments show that our method efficiently produces visually pleasing panoramas with regular boundaries and unnoticeable distortions.

show abstract

“…5 gives comparison with state-of-the-art methods in terms of line preserving. In [4], the line segment detection is used for feature preserving in global transformation, like scale…”

Section: Results and Applicationsmentioning

confidence: 99%

Section: A Results and Comparisonsmentioning

confidence: 99%

Section: Initial Image Stitchingmentioning

confidence: 99%

“…For any other image I i (2 ≤ i ≤ N ), the desired scaling s i and rotation angle θ i w.r.t. I 1 are calculated according to [4]. The global similarity term is defined as…”

Section: Initial Image Stitchingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Content-Preserving Image Stitching With Piecewise Rectangular Boundary Constraints

Yun

Lai

Zhang

2021

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

show abstract

Robust Image Stitching with Multiple Registrations

Herrmann

Wang

Bowen

et al. 2018

Computer Vision – ECCV 2018

View full text Add to dashboard Cite

Object-Centered Image Stitching

Herrmann

Wang

Bowen

et al. 2018

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Image stitching is typically decomposed into three phases: registration, which aligns the source images with a common target image; seam finding, which determines for each target pixel the source image it should come from; and blending, which smooths transitions over the seams. As described in [1], the seam finding phase attempts to place seams between pixels where the transition between source images is not noticeable. Here, we observe that the most problematic failures of this approach occur when objects are cropped, omitted, or duplicated. We therefore take an object-centered approach to the problem, leveraging recent advances in object detection [2,3,4]. We penalize candidate solutions with this class of error by modifying the energy function used in the seam finding stage. This produces substantially more realistic stitching results on challenging imagery. In addition, these methods can be used to determine when there is non-recoverable occlusion in the input data, and also suggest a simple evaluation metric that can be used to evaluate the output of stitching algorithms.

show abstract

Natural Image Stitching with the Global Similarity Prior

Cited by 177 publications

References 16 publications

Content-Preserving Image Stitching With Piecewise Rectangular Boundary Constraints

Content-Preserving Image Stitching With Piecewise Rectangular Boundary Constraints

Robust Image Stitching with Multiple Registrations

Object-Centered Image Stitching

Contact Info

Product

Resources

About