Image melding

By Soheil Darabi, Eli Shechtman, Connelly Barnes, Dan B. Goldman, Pradeep Sen. ACM Transactions on Graphics, 2012

335 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/fd61d60c446a491c6110d568841ca594391b38e6

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

Flow-edge Guided Video Completion (2020, methodology): “In addition to using only verbatim copied patches, several methods improve the completion quality by augmenting patch search with geometric and photometric transformations [8,13,15,24].”
3D Photography Using Context-Aware Layered Depth Inpainting (2020, methodology): “Inspired by the success of texture synthesis [9, 8], examplebased methods complete the missing regions by transferring the contents from the known regions of the image, either through non-parametric patch-based synthesis [58, 1, 5, 20] or solving a Markov Random Field model using belief propagation ”
Image completion using planar structure guidance (2014, methodology): “Image Melding, while theoretically equipped with the ability to apply appropriate scaling of the patches, fails to ﬁnd such solution in high-dimensional space.”
StructureFlow: Image Inpainting via Structure-Aware Appearance Flow (2019, background): “Patch-based methods [1, 8, 3] fill target regions by searching and copying similar image patches from the uncorrupted regions of the source images.”
Image Inpainting : Overview and Recent Advances (2014, methodology): “Image melding [46] synthesizes the texture in the transition region by transforming one patch (or image) to be stitched into the other.”
Guided Image Inpainting: Replacing an Image Region by Pulling Content From Another Image (2018, methodology): “Image melding uses patch-based synthesis to resolve texture inconsistencies when transferring content from the guidance image to the source image [7].”
Progressive Image Inpainting with Full-Resolution Residual Network (2019, methodology): “These methods often aim to minimize discontinuities in an iterative way [5, 10].”
Faceshop (2018, background): “PatchMatch [Barnes et al. 2009] accelerates the patch search algorithm to enable image completion at interactive frame rates, and Image Melding [Darabi et al. 2012] further improves the quality of the patch search algorithm.”
Stable and Controllable Neural Texture Synthesis and Style Transfer Using Histogram Losses (2017, methodology): “In computer graphics, color adjustment models based on afﬁne operations are often explored for ﬁnding correspondences [HaCohen et al. 2011], and adjusting colors [Siddiqui and Bouman 2008], including for texture synthesis [Darabi et al. 2012; Diamanti et al. 2015].”
Coherent Semantic Attention for Image Inpainting (2019, background): “Non-learning approaches such as [11, 1, 3, 5, 6, 9, 15, 2, 32, 18, 34, 28, 12, 29] fill in missing regions by propagating neighboring information or copying information from similar patch of the background.”