Image Completion Using Global Optimization

By Nikos Komodakis. Computer Vision and Pattern Recognition, 2006

294 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/dadc3e91d38a691202b39835dfb5108c28f01c35

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

SPG-Net: Segmentation Prediction and Guidance Network for Image Inpainting (2018, background): “Image inpainting is the task to reconstruct the missing region in an image with plausible contents based on its surrounding context, which is a common topic of low-level computer vision [12, 18].”
Interactive image completion with perspective correction (2006, methodology): “[23] propose a global texture optimization and very recently Komodakis and Tziritas [22] proposed a global optimization method for image completion.”
Shift-map image editing (2009, background): “The inherent problems of using patches are also affecting the object removal in [9].”
MRF Energy Minimization and Beyond via Dual Decomposition (2011, unknown): “For instance, to mention a few of their applications in vision, discrete MRFs have been used extensively in stereo matching [47], [31], [19], image segmentation [27], optical flow estimation [37], image denoising [11], texture synthesis [29], image completion [25], and object recognition [10].”
Missing Data Reconstruction in Remote Sensing Image With a Unified Spatial–Temporal–Spectral Deep Convolutional Neural Network (2018, methodology): “based methods [17]–[19], partial differential equation (PDE)based methods [20], [21], variational methods [22], [23], and”
Image Inpainting using Block-wise Procedural Training with Annealed Adversarial Counterpart (2018, background): “It is one of the most common operations of image editing [7] and low-level computer visions [16, 9].”
Missing Information Reconstruction of Remote Sensing Data: A Technical Review (2015, methodology): “The patch or pixel locations are optimized in MRF by the use of belief propagation [21] or graph cuts [33].”
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 : Overview and Recent Advances (2014, methodology): “In [36], an energy term comprising a texture synthesis term and a term measuring how patches to be stitched together agree in the overlap area is minimized using belief propagation.”
Shift-Net: Image Inpainting via Deep Feature Rearrangement (2018, methodology): “Global image coherence has also been introduced to the Markov random ﬁeld (MRF) framework for improving visual quality [22, 32, 43].”
Tensor completion for estimating missing values in visual data (2010, background): “In computer vision and graphics, many problems can be formulated as the missing value estimation problem, e.g. image in-painting [4] [12] [11], video decoding, video inpainting , scan completion, and appearance acquisition completion .”
Statistics of Patch Offsets for Image Completion (2012, unknown): “Comparison with Priority-BP [14].”
Image Completion Using Efficient Belief Propagation Via Priority Scheduling and Dynamic Pruning (2007, background): “Before proceeding, we should also mention that a much less detailed description of this work has appeared in CVPR 2006 [28].”
Fast and Accurate Matrix Completion via Truncated Nuclear Norm Regularization (2013, background): “This problem occurs in many real applications in computer vision and pattern recognition, such as image inpainting [8], [9], video denoising [10], and recommender systems [11], [12].”