Image completion using planar structure guidance

By Jia-Bin Huang, Sing Bing Kang, Narendra Ahuja, Johannes Peter Kopf. 2014

377 citations recorded by the source corpus.

Subfields: 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 Computer Graphics and Computer-Aided Design

In Computer Vision and Pattern Recognition

Citations in the corpus

Semantic Understanding of Scenes Through the ADE20K Dataset (2016, methodology): “f the automatic image content removal. It can be seen that with the object score maps, we are able to crop out the objects from an image precisely. The image completion technique used is described in [14]. Semantic Understanding of Scenes through the ADE20K Dataset 17 !"#$%& '()* +(,-&”
EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning (2019, background): “Patch-based methods, on the other hand, fill in missing regions with patches from a collection of source images that maximize patch similarity [7, 21].”
Free-Form Image Inpainting With Gated Convolution (2018, methodology): “To improve image inpainting, user guidance is explored including dots or lines [1, 3, 7, 40], structures [13], transformation or distortion information [14, 30] and image exemplars [4, 10, 20, 43, 51].”
Semantic Image Inpainting with Deep Generative Models (2016, background): “Prior knowledge, such as statistics of patch offsets [11], planarity [13] or low rank (LR) [12] can greatly improve the result as well.”
Scene Parsing through ADE20K Dataset (2017, methodology): “We used the image completion technique described in [14].”
Selfie: Self-supervised Pretraining for Image Embedding (2019, background): “…with an unperturbed image (Exemplar) (e.g., Dosovitskiy et al. (2016)), 3) predicting relative locations of patches (e.g., Doersch et al. (2015)), solving Jigsaw puzzles (e.g., Noroozi and Favaro (2016)) and 4) impainting (e.g., Huang et al. (2014); Pathak et al. (2016); Iizuka et al. (2017)).”
Pluralistic Image Completion (2019, background): “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.”
Coherent Semantic Attention for Image Inpainting (2019, background): “[14] blend the known regions into the target regions to minimize discontinuities.”
Progressive Image Inpainting with Full-Resolution Residual Network (2019, methodology): “These methods often aim to minimize discontinuities in an iterative way [5, 10].”
Single image super-resolution from transformed self-exemplars (2015, methodology): “D affine motion parameter of the source patch and m i is the index of detected plane (using [20]).”
Robust Image Completion via Deep Feature Transformations (2019, background): “Prior knowledge, such as statistics of patch offsets [61], planarity [62] or low rank (LR) [61] can greatly improve the result as well.”
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 ”
Generative Face Completion (2017, background): “Although similar patches or images may be found, the unique patterns of objects that involve semantic representation are not well modeled, since both low-level [2] and mid-level [10] visual cues of the known regions are not sufﬁcient to infer semantically valid contents in missing regions.”
Image Inpainting Using Nonlocal Texture Matching and Nonlinear Filtering (2019, methodology): “[28], 5) exemplar-based image inpainting using a modified priority definition by Deng et al.”
Context-Aware Semantic Inpainting (2017, methodology): “The second experiment in this section compares our method with other state-of-the-art inpainting methods [1], [2], [7], [8], [19], [45] on the Paris StreetView”
Semantic Image Inpainting with Perceptual and Contextual Losses (2016, background): “Certain subsets of images could also contain special properties, such as being planar [12] or having a low rank structure [11]; reconstruction results can be greatly improved by taking into consideration these prior knowledge.”
Foreground-Aware Image Inpainting (2019, background): “[11] explicitly utilize planar structures as guidance to rectify perspectively-distorted textures.”
EdgeConnect: Structure Guided Image Inpainting using Edge Prediction (2019, background): “Patch-based meth-ods, on the other hand, ﬁll in missing regions with patches from a collection of source images that maximize patch similarity [8, 23].”
Meta-representation of shape families (2014, background): “As a high-resolution alternative, Huang et al. [2012] proposed a multilayer device that relies on prefiltered image content.”