Globally and locally consistent image completion

By Satoshi Iizuka, Edgar Simo-Serra, Hiroshi Ishikawa. 2017

2,208 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

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

In Media Technology

Citations in the corpus

Progressive Growing of GANs for Improved Quality, Stability, and Variation (2017, background): “…methods that produce novel samples from high-dimensional data distributions, such as images, are ﬁnding widespread use, for example in speech synthesis (van den Oord et al., 2016a), image-to-image translation (Zhu et al., 2017; Liu et al., 2017), and image inpainting (Iizuka et al., 2017).”
Resolution-robust Large Mask Inpainting with Fourier Convolutions (2021, methodology): “Towards this end, [18] proposed to incorporate dilated convolutions [55] to expand receptive field; besides, two discriminators were supposed to encourage global and local consistency separately.”
Large Scale Image Completion via Co-Modulated Generative Adversarial Networks (2021, background): “…multi-stage architectures, specialized operations, or intermediate structures like edges or contours (Altinel et al., 2018; Ding et al., 2018; Iizuka et al., 2017; Jiang et al., 2019; Lahiri et al., 2020; Li et al., 2020; Liu et al., 2018; 2019a; 2020; Nazeri et al., 2019; Ren et al., 2019;…”
Regionwise Generative Adversarial Image Inpainting for Large Missing Areas (2019, methodology): “rsarial network on real images, then they recovered the encoding of the corrupted image to the “closest” intact one while being constrained to the real image manifold. Meanwhile, in the work of GLCIC [47], global and local context discriminators were utilized to distinguish real images from complete”
EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning (2019, methodology): “1Model by [22] required two months of training over four GPUs.”
Free-Form Image Inpainting With Gated Convolution (2018, methodology): “For previous inpainting networks which try to fill a single rectangular hole, an additional local GAN is used on the masked rectangular region to improve results [15, 49].”
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs (2017, background): “[20] add a global image classifier to conditional GANs to synthesize globally coherent content for inpainting.”
A Hybrid Model for Identity Obfuscation by Face Replacement (2018, methodology): “he parametric model in Stage-I with a GAN. We use the same architecture as the stage-II network of [1], but without the landmark channel. This is inspired by the regional completion method using GANs [44]. We consider two comparison scenarios: when the input face is blacked-out (indexed by v13), we ”
Deep Image Prior (2017, neutral): “We compare to a learning-based method of [15] in fig.”
Palette: Image-to-Image Diffusion Models (2021, methodology): “GANs are widely used but often require auxiliary objectives on structures, context, edges, contours and hand-engineered features [Iizuka et al. 2017; Kim et al. 2021a; Liu et al. 2020; Nazeri et al. 2019; Yi et al. 2020; Yu et al. 2018b, 2019], and they lack diversity in their outputs [Zhao et al.”
Image Inpainting for Irregular Holes Using Partial Convolutions (2018, methodology): “2(c): inpainted result of Iizuka et al.[10].”
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)).”
Contextual-Based Image Inpainting: Infer, Match, and Translate (2017, background): “It is also able to fill in holes of arbitrary shapes, and can handle much larger holes than [15].”
Pluralistic Image Completion (2019, methodology): “This was followed by several CNN-based methods, which included combining global and local discriminators as adversarial loss [14], identifying closest features in the latent space of masked images [40], utilizing semantic labels to guide the completion network [36], introducing additional face parsi”
Image Inpainting via Generative Multi-column Convolutional Neural Networks (2018, methodology): “In fact, adversarial loss has already been used in recent methods [18, 25, 24, 9, 26] to learn multi-modality.”
FakeCatcher: Detection of Synthetic Portrait Videos using Biological Signals (2019, methodology): “Following the Generative Adversarial Networks proposed by Goodfellow et al. [22], deep learning models have been advancing for generative tasks for inpainting [27], translation [62], and editing [11].”
Towards Photo-Realistic Virtual Try-On by Adaptively Generating↔Preserving Image Content (2020, background): “Beneﬁted from the powerful ability of GAN, it enjoys pervasive applications on tasks such as style transfer [52, 3], image inpainting [45, 15, 47, 48, 27], and image editing [20, 5, 24, 31].”