Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

computer-vision-4

Image Outpainting

3260 papers • 126 benchmarks • 313 datasets

Predicting the visual context of an image beyond its boundary. Image credit: NUWA-Infinity: Autoregressive over Autoregressive Generation for Infinite Visual Synthesis

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in image-outpainting-4

Trend

Dataset

Best Model

Actions

LHQC

LHQC

Places365-Standard

Places365-Standard

MSCOCO

MSCOCO

Libraries

i

Use these libraries to find image-outpainting-4 models and implementations

Datasets

Places365

LHQ

Subtasks

No subtasks available.

Most implemented papers

Taming Transformers for High-Resolution Image Synthesis

Robin Rombach, B. Ommer, Patrick Esser•Wed Dec 16 2020

It is demonstrated 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.

3866

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

0

MaskGIT: Masked Generative Image Transformer

Lu Jiang, Ce Liu, Huiwen Chang, Han Zhang, W. Freeman•Mon Feb 07 2022

The proposed MaskGIT is a novel image synthesis paradigm using a bidirectional transformer decoder that significantly outperforms the state-of-the-art transformer model on the ImageNet dataset, and accelerates autoregressive decoding by up to 48x.

922 0

Painting Outside the Box: Image Outpainting with GANs

Gili Rusak, Mark Sabini•Fri Aug 24 2018

A deep learning approach based on Iizuka et al. for adversarially training a network to hallucinate past image boundaries to show that deep learning approaches to image outpainting are both feasible and promising.

81 0

Wide-Context Semantic Image Extrapolation

Xiaoyong Shen, Jiaya Jia, Xin Tao, Yi Wang•Fri May 31 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. This seemingly easy task actually faces many crucial technical challenges and has its unique properties. The two major issues are size expansion and one-side constraints. We propose a semantic regeneration network with several special contributions and use multiple spatial related losses to address these issues. Our results contain consistent structures and high-quality textures. Extensive experiments are conducted on various possible alternatives and related methods. We also explore the potential of our method for various interesting applications that can benefit research in a variety of fields.

111 0

Image Outpainting and Harmonization using Generative Adversarial Networks

Basile Van Hoorick•Sun Dec 22 2019

It is demonstrated that GANs hold powerful potential in producing reasonable extrapolations and two outpainting methods are proposed that aim to instigate this line of research, using a context encoder inspired by common inpainting architectures and paradigms.

36 0

0.5 Petabyte Simulation of a 45-Qubit Quantum Circuit

Thomas Häner, Damian S. Steiger•Mon Apr 03 2017

This work applies a scheduling algorithm to quantum supremacy circuits in order to reduce the required communication and simulate a 45-qubit circuit on the Cori II supercomputer using 8, 192 nodes and 0.5 petabytes of memory, which constitutes the largest quantum circuit simulation to this date.

200 0

Multimodal Image Outpainting with Regularized Normalized Diversification

Lingzhi Zhang, Jianbo Shi, Jiancong Wang•Thu Oct 24 2019

This paper proposes a new regularization method to encourage diverse sampling in conditional synthesis and proposes a feature pyramid discriminator to improve the image quality.

18 0

Enhanced Residual Networks for Context-based Image Outpainting

Przemek Gardias, Eric Arthur, Huaming Sun•Wed May 13 2020

Comparisons of the model and the baseline's L1 loss, mean squared error (MSE) loss, and qualitative differences reveal the model is able to naturally extend object boundaries and produce more internally consistent images compared to current methods but produces lower fidelity images.

6 0

Very Long Natural Scenery Image Prediction by Outpainting

Shuicheng Yan, Yi Yang, Ping Liu, Zongxin Yang, Jian Dong•Mon Sep 30 2019

This work devise some innovative modules, named Skip Horizontal Connection and Recurrent Content Transfer, and integrate them into their designed encoder-decoder structure, and shows that this network can generate highly realistic outpainting prediction effectively and efficiently.

96 0

SiENet: Siamese Expansion Network for Image Extrapolation

Xiaofeng Zhang, Ming Tao, Feng Chen, Cailing Wang, Guoping Jiang•Tue Jul 07 2020

A novel two-stage siamese adversarial model for image extrapolation, named Siamese Expansion Network (SiENet) is proposed, designed for allowing encoder to predict the unknown content, alleviating the burden of decoder.

61 0

Adding a benchmark result helps the community track progress.

Image Outpainting | State-of-the-Art