Image Inpainting

270 papers with code • 12 benchmarks • 17 datasets

Image Inpainting is a task of reconstructing missing regions in an image. It is an important problem in computer vision and an essential functionality in many imaging and graphics applications, e.g. object removal, image restoration, manipulation, re-targeting, compositing, and image-based rendering.

Source: High-Resolution Image Inpainting with Iterative Confidence Feedback and Guided Upsampling

Image source: High-Resolution Image Inpainting with Iterative Confidence Feedback and Guided Upsampling

Libraries

Use these libraries to find Image Inpainting models and implementations

Most implemented papers

Semantic Image Inpainting with Deep Generative Models

bamos/dcgan-completion.tensorflow CVPR 2017

In this paper, we propose a novel method for semantic image inpainting, which generates the missing content by conditioning on the available data.

Resolution-robust Large Mask Inpainting with Fourier Convolutions

saic-mdal/lama 15 Sep 2021

We find that one of the main reasons for that is the lack of an effective receptive field in both the inpainting network and the loss function.

Contextual Residual Aggregation for Ultra High-Resolution Image Inpainting

Atlas200dk/sample-imageinpainting-HiFill CVPR 2020

Since convolutional layers of the neural network only need to operate on low-resolution inputs and outputs, the cost of memory and computing power is thus well suppressed.

Deep Fusion Network for Image Completion

researchmm/PEN-Net-for-Inpainting 17 Apr 2019

The fusion block not only provides a smooth fusion between restored and existing content, but also provides an attention map to make network focus more on the unknown pixels.

Joint learning of variational representations and solvers for inverse problems with partially-observed data

CIA-Oceanix/4dvarnet-core 5 Jun 2020

The variational cost and the gradient-based solver are both stated as neural networks using automatic differentiation for the latter.

SC-FEGAN: Face Editing Generative Adversarial Network with User's Sketch and Color

run-youngjoo/SC-FEGAN ICCV 2019

We present a novel image editing system that generates images as the user provides free-form mask, sketch and color as an input.

High-Fidelity Pluralistic Image Completion with Transformers

raywzy/ICT ICCV 2021

Image completion has made tremendous progress with convolutional neural networks (CNNs), because of their powerful texture modeling capacity.

Image Inpainting via Conditional Texture and Structure Dual Generation

xiefan-guo/ctsdg ICCV 2021

Deep generative approaches have recently made considerable progress in image inpainting by introducing structure priors.

CVAE-GAN: Fine-Grained Image Generation through Asymmetric Training

Ram81/AC-VAEGAN-PyTorch ICCV 2017

Our approach models an image as a composition of label and latent attributes in a probabilistic model.

Variational Autoencoder with Arbitrary Conditioning

tigvarts/ucm ICLR 2019

We propose a single neural probabilistic model based on variational autoencoder that can be conditioned on an arbitrary subset of observed features and then sample the remaining features in "one shot".