Object removal by exemplar-based inpainting

By Antonio Criminisi, Patrick Pérez, Kentaro Toyama. 2003

1,183 citations recorded by the source corpus.

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

How researchers see this paper

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

In Computational Mechanics

In Computer Graphics and Computer-Aided Design

In Computer Vision and Pattern Recognition

Citations in the corpus

Resolution-robust Large Mask Inpainting with Fourier Convolutions (2021, background): “The subject has been studied in pre-deep learning era [1, 5, 13], and the progress accelerated in recent years through the use of deep and wide neural networks [26, 30, 25] and adversarial learning [34, 18, 56, 44, 57, 32, 54, 61].”
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].”
Pluralistic Image Completion (2019, methodology): “Early image completion works [4, 7, 5, 8, 3, 13] focus only on steps 2 and 3 above, by assuming that gaps should be filled with similar content to that of the background.”
Full-frame video stabilization with motion inpainting (2006, background): “The idea of motion inpainting is propagating local motion, instead of color/intensity as in image inpainting [27], [28], into the missing image areas.”
Inpaint Anything: Segment Anything Meets Image Inpainting (2023, background): “Remove Anything focuses on the object removal problem [2, 3, 5] by allowing users to eliminate any object from an image while ensuring that the resulting image remains visually plausible.”
Image completion with structure propagation (2005, methodology): “Recent example-based methods work at the image patch level [Drori et al. 2003; Criminisi et al. 2003; Bertalmio et al. 2003; Jia and Tang 2003].”
Fast Anisotropic Smoothing of Multi-Valued Images using Curvature-Preserving PDE's (2006, background): “It is also worth to cite some papers related to inpainting without use of PDE’s (Criminisi et al., 2003; Jia and Tang, 2003), among others.”
Learning how to inpaint from global image statistics (2003, methodology): “used an exampler-based approach, adapting the synthesis method of Efros and Leung [9] to image inpainting [5].”
Sparse Representation for Color Image Restoration (2008, methodology): “For larger holes, iterative and/or multiscale or texture synthesis methods like in [50] are needed.”
PatchMatch: a randomized correspondence algorithm for structural image editing (2009, methodology): “Other algorithms for image completion let a user simply erase an unwanted portion of an image, and the computer automatically synthesizes a fill region that plausibly matches the remainder of the image [Criminisi et al. 2003; Komodakis and Tziritas 2007].”
A Survey of Human-in-the-loop for Machine Learning (2021, methodology): “The image inpainting frameworks proposed by previous studies can be bifurcated as exemplarbased [96] approaches and deep learning-based [97] methods.”
Space-Time Completion of Video (2007, methodology): “Each is then filled incrementally using the priority-based ordering idea similar to [9].”
Guided Image Inpainting: Replacing an Image Region by Pulling Content From Another Image (2018, methodology): “Automated image inpainting is an established computer vision problem with many valuable applications [16, 37, 6, 9, 38, 27, 45].”
Non-local sparse models for image restoration (2009, background): “This model should also prove of interest in deblurring and inpainting tasks that have become the topic of much recent research (e.g., [2] [6] [23]) with the emergence of computational photography.”
Image Completion Using Efficient Belief Propagation Via Priority Scheduling and Dynamic Pruning (2007, methodology): “This is in contrast to the state-of-the-art method in [ 27 ], where the authors had to hardwire isophote-”
Region filling and object removal by exemplar-based image inpainting (2004, background): “This paper builds upon and extends the work in [8], with a more detailed description of the algorithm and extensive comparisons with the state of the art.”
TextonBoost for Image Understanding: Multi-Class Object Recognition and Segmentation by Jointly Modeling Texture, Layout, and Context (2007, background): “24, options could be given to automatically erase the object from the image (using image in-painting, e.g. Criminisi et al. 2004), change the focus of background, fix red eye, or adjust the color balance just for that object.”