Image Completion Using Efficient Belief Propagation Via Priority Scheduling and Dynamic Pruning

By Nikos Komodakis, G. Tziritas. IEEE Transactions on Image Processing, 2007

377 citations recorded by the source corpus.

Subfields: Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/deabccf84a8160a5f6ddaf3e554534386849760e

How researchers see this paper

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

In Computer Graphics and Computer-Aided Design

In Computer Vision and Pattern Recognition

Citations in the corpus

Image completion using planar structure guidance (2014, methodology): “In the supplementary material we also compare against Priority Belief Propagation [Komodakis and Tziritas 2007] and GIMP Resynthesizer2.”
Transformation guided image completion (2013, methodology): “Most automatic techniques (such as [1, 7, 6, 22, 14, 8]) are able to handle a specific set of structural conditions, but mostly fine to mid-level textures.”
High-Resolution Image Inpainting Using Multi-scale Neural Patch Synthesis (2016, background): “The first group of approaches relies on texture synthesis techniques, which fills in the hole by extending textures from surrounding regions [14, 13, 27, 26, 6, 12, 40, 41, 23, 24, 2].”
Image Inpainting With Learnable Bidirectional Attention Maps (2019, methodology): “To guide the patch processing order, patch priority [15, 29] measure has been introduced as the product of confidence term and data term.”
Context-Aware Semantic Inpainting (2017, positive): “[22] proposed a priority belief propagation method.”
Image Inpainting by Patch Propagation Using Patch Sparsity (2010, background): “More examplar-based inpainting algorithms [14]–[16]were also proposed for image completion.”
Shift-Net: Image Inpainting via Deep Feature Rearrangement (2018, methodology): “In exemplar-based inpainting [2, 3, 5, 7, 9, 17, 18, 22, 23, 25, 32, 37, 39, 43, 44, 46], the completion is conducted from the exterior to the interior of the missing part by searching and copying best matching patches from the known region.”
The patch transform and its applications to image editing (2008, methodology): “Kwatra et al. [17], and Komodakis and Tziritas [16] employed related Markov random field models, solved using graph cuts or belief propagation , for texture synthesis and image completion.”
Optical flow modeling and computation: A survey (2015, methodology): “Inpainting methods can be coarsely divided into two classes, diffusion-based methods [24,56] and exemplar-based methods [6,68,151].”
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 ”
Statistics of Patch Offsets for Image Completion (2012, methodology): “Comparison with Priority-BP [14].”
PatchMatch: a randomized correspondence algorithm for structural image editing (2009, methodology): “Even the most advanced global optimization based methods [Wexler et al. 2007; Komodakis and Tziritas 2007] can still produce inconsistencies where structured content is inpainted (e.”