Image Inpainting by Patch Propagation Using Patch Sparsity

By Zongben Xu, Jian Sun. IEEE Transactions on Image Processing, 2010

601 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/4f0f17759ca9dfdb8afa66d156f26e621da0c92e

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

Rethinking Image Inpainting via a Mutual Encoder-Decoder with Feature Equalizations (2020, methodology): “ver, they only consider surrounding pixels of missing regions, which can only deal with small holes in background inpainting tasks and may fail to generate meaningful structures. In contrast, methods [4,5,28,2,36] based on patch match ll missing regions by transferring similar and relevant patches f”
Image Inpainting With Learnable Bidirectional Attention Maps (2019, background): “Xu and Sun [32] assumed that structural patches are sparsely distributed in an image, and presented a sparsity-based data term.”
Image Inpainting with Learnable Feature Imputation (2020, background): “For example, pattern matching, by searching and replacing with similar patches [4,8,23,29,38,43], or diffusion-based, by smoothly propagating information from the boundary of the missing area [3,5,6].”
Image Inpainting : Overview and Recent Advances (2014, methodology): “Therefore, instead of using pre-defined waveforms, a linear combination of candidate patches regularized by a sparseness prior on the weighting coefficients can be used for inferring the unknown pixels [32].”
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.”
Text-Guided Neural Image Inpainting (2020, background): “Image inpainting Traditional diffusion-based or patch-based approaches [27, 31] fill missing regions by propagating neighbor information[2, 37] or copying from similar patches [8, 36] of the background based on low-level features.”
Semantic Image Inpainting with Progressive Generative Networks (2018, background): “Although non-semantic image inpainting approaches have been studied for decades [2, 5– 7, 9, 17, 25, 27, 31], they cannot generate semantically meaningful content, and thus are not suitable to handle the semantic image inpainting task where large proportions of areas are corrupted in images.”
Shift-Net: Image Inpainting via Deep Feature Rearrangement (2018, background): “For better recovery of image structure, several patch priority measures have been proposed to ﬁll in structural patches ﬁrst [5, 25, 46].”
Mask-Specific Inpainting with Deep Neural Networks (2014, methodology): “6 shows the results for one out of five images from [26] (Fig.”
Progressive Image Inpainting with Full-Resolution Residual Network (2019, methodology): “When it comes to traditional inpainting methods, we can further divide them into two sub-categories: diffusion-based methods [1, 3, 4, 7, 15, 17] and patch-based methods [2, 5, 6, 10, 24, 30].”
Solving Linear Inverse Problems Using Gan Priors: An Algorithm with Provable Guarantees (2018, background): “Several works (including [22, 23, 24]) employ sparsity priors to solve inverse problems such as denoising, super-resolution and inpainting.”
Contextual Residual Aggregation for Ultra High-Resolution Image Inpainting (2020, background): “Another stream is relying on texture synthesis techniques, which fills the hole by both extending and borrowing textures from surrounding regions [3, 4, 5, 6, 7].”
Context-Aware Semantic Inpainting (2017, methodology): “Some existing methods for image completion are related to texture synthesis [16], [17] or patch-based synthesis [18], [19], [20].”
Transformation guided image completion (2013, methodology): “[26] use patch sparsity to guide the filling process.”
Diversity-Generated Image Inpainting with Style Extraction (2019, background): “Xu et al. [8] proposed a typical inpainting method which involves investigating the spatial distribution of image patches.”