Seamless Image Stitching in the Gradient Domain

By Anat Levin, Assaf Zomet, Shmuel Peleg, Yair Weiss. European Conference on Computer Vision, 2004

592 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/ccc8020897b023375b70acf0cd1debadd999986c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

GP-GAN: Towards Realistic High-Resolution Image Blending (2017, unknown): “me registration errors or fast moving objects between the source images. Burt and Adelson [4] present a ﬁxing solution so-called multiband blending algorithm. Alternatively, gradient-based approaches [21,35,9,1,16,18,30] also address this problem by adjusting the differences in color and illuminatio”
High-Resolution Image Inpainting with Iterative Confidence Feedback and Guided Upsampling (2020, methodology): “object removal, image restoration, manipulation, re-targeting, compositing, and image-based rendering [9,26,33] Classical inpainting methods such as [17,25,9] typically rely on the principle of borrowing example patches from known regions or external database images and pasting them into the holes.”
Locally adapted hierarchical basis preconditioning (2006, methodology): “It has since been extended to non-linear variants [Levin et al. 2004b], as well as applied to image stitching, where it is used to reduce visual discontinuities across image seams [Agarwala et al. 2004].”
Learning Pyramid-Context Encoder Network for High-Quality Image Inpainting (2019, background): “This task has drawn great attention and become a valuable and active research topic for decades [5, 12, 17], because high-quality”
PEPSI : Fast Image Inpainting With Parallel Decoding Network (2019, background): “Image inpainting techniques have been widely researched [1–3, 5, 6, 10, 13, 16, 17, 19, 21, 25, 26, 28] for removing an unwanted object or synthesizing missing parts of an image in various applications such as photo editing, image-based rendering, and computational photography [15, 20, 28].”
Constructing image panoramas using dual-homography warping (2011, methodology): “The first is to blend the entire overlapped region, such techniques include feathering techniques [22], multi-band blending [7] and gradient domain stitching [14].”
Generative Image Inpainting with Contextual Attention (2018, methodology): “It has many applications in photo editing, image-based rendering and computational photography [3, 23, 28, 29, 34, 39].”
Image super-resolution using gradient profile prior (2008, unknown): “This kind of “sparseness prior” has been successfully applied to super-resolution[28], denoising [23] [24], inpainting [17], transparency separation [16] and deblurring [8, 15].”
A Unified Framework for Street-View Panorama Stitching (2016, background): “In the last several decades, many image blending algorithms have been proposed to smooth the color differences along the seam lines, such as feathering [47], alpha blending [48], Laplacian pyramid blending [49], Poisson blending [50] and the gradient domain image blending approach [51].”