Image Outpainting
22 papers with code • 3 benchmarks • 4 datasets
Predicting the visual context of an image beyond its boundary.
Image credit: NUWA-Infinity: Autoregressive over Autoregressive Generation for Infinite Visual Synthesis
Benchmarks
These leaderboards are used to track progress in Image Outpainting
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
MS COCO
MSCOCO
Places365
LHQ
Most implemented papers
Taming Transformers for High-Resolution Image Synthesis
CompVis/taming-transformers
•
•
CVPR 2021
We demonstrate how combining the effectiveness of the inductive bias of CNNs with the expressivity of transformers enables them to model and thereby synthesize high-resolution images.
MaskGIT: Masked Generative Image Transformer
google-research/maskgit
•
•
CVPR 2022
At inference time, the model begins with generating all tokens of an image simultaneously, and then refines the image iteratively conditioned on the previous generation.
Painting Outside the Box: Image Outpainting with GANs
ShinyCode/image-outpainting
•
•
The challenging task of image outpainting (extrapolation) has received comparatively little attention in relation to its cousin, image inpainting (completion).
Wide-Context Semantic Image Extrapolation
shepnerd/outpainting_srn
•
•
CVPR 2019
This paper studies the fundamental problem of extrapolating visual context using deep generative models, i. e., extending image borders with plausible structure and details.
Image Outpainting and Harmonization using Generative Adversarial Networks
basilevh/image-outpainting
•
•
This way, the hallucinated details are integrated with the style of the original image, in an attempt to further boost the quality of the result and possibly allow for arbitrary output resolutions to be supported.
0.5 Petabyte Simulation of a 45-Qubit Quantum Circuit
Near-term quantum computers will soon reach sizes that are challenging to directly simulate, even when employing the most powerful supercomputers.
Multimodal Image Outpainting With Regularized Normalized Diversification
In this paper, we study the problem of generating a set ofrealistic and diverse backgrounds when given only a smallforeground region.
Very Long Natural Scenery Image Prediction by Outpainting
z-x-yang/NS-Outpainting
•
•
ICCV 2019
The second challenge is how to maintain high quality in generated results, especially for multi-step generations in which generated regions are spatially far away from the initial input.
Enhanced Residual Networks for Context-based Image Outpainting
Although humans perform well at predicting what exists beyond the boundaries of an image, deep models struggle to understand context and extrapolation through retained information.
SiENet: Siamese Expansion Network for Image Extrapolation
nanjingxiaobawang/SieNet-Image-extrapolation
•
•
In this paper, a novel two-stage siamese adversarial model for image extrapolation, named Siamese Expansion Network (SiENet) is proposed.
