254 papers with code • 12 benchmarks • 16 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.
Existing deep learning based image inpainting methods use a standard convolutional network over the corrupted image, using convolutional filter responses conditioned on both valid pixels as well as the substitute values in the masked holes (typically the mean value).
Motivated by these observations, we propose a new deep generative model-based approach which can not only synthesize novel image structures but also explicitly utilize surrounding image features as references during network training to make better predictions.
By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond.
However, current network architectures for such implicit neural representations are incapable of modeling signals with fine detail, and fail to represent a signal's spatial and temporal derivatives, despite the fact that these are essential to many physical signals defined implicitly as the solution to partial differential equations.
The edge generator hallucinates edges of the missing region (both regular and irregular) of the image, and the image completion network fills in the missing regions using hallucinated edges as a priori.
We introduce a new generative model where samples are produced via Langevin dynamics using gradients of the data distribution estimated with score matching.
Combined with multiple architectural improvements, we achieve record-breaking performance for unconditional image generation on CIFAR-10 with an Inception score of 9. 89 and FID of 2. 20, a competitive likelihood of 2. 99 bits/dim, and demonstrate high fidelity generation of 1024 x 1024 images for the first time from a score-based generative model.
In this paper, we propose a novel method for semantic image inpainting, which generates the missing content by conditioning on the available data.