# Image Outpainting and Harmonization using Generative Adversarial Networks

arXiv: https://arxiv.org/abs/1912.10960 · HTML: https://mlsanity.com/paper/1912.10960/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Dec 2019.

## Built on by (most cited first, 12 of 12)

- [Street-View Image Generation from a Bird's-Eye View Layout](https://mlsanity.com/paper/2301.04634/) (2023)
- [Aligning Latent and Image Spaces to Connect the Unconnectable](https://mlsanity.com/paper/2104.06954/) (2021)
- [Making Images Real Again: A Comprehensive Survey on Deep Image Composition](https://mlsanity.com/paper/2106.14490/) (2021)
- [Autoregressive Omni-Aware Outpainting for Open-Vocabulary 360-Degree Image Generation](https://mlsanity.com/paper/2309.03467/) (2023)
- [DiffInfinite: Large Mask-Image Synthesis via Parallel Random Patch Diffusion in Histopathology](https://mlsanity.com/paper/2306.13384/) (2023)
- [Continuous-Multiple Image Outpainting in One-Step via Positional Query and A Diffusion-based Approach](https://mlsanity.com/paper/2401.15652/) (2024)
- [Outpainting by Queries](https://mlsanity.com/paper/2207.05312/) (2022)
- [Yformer: U-Net Inspired Transformer Architecture for Far Horizon Time Series Forecasting](https://mlsanity.com/paper/2110.08255/) (2021)
- [Generalised Image Outpainting with U-Transformer](https://mlsanity.com/paper/2201.11403/) (2022)
- [VIP: Versatile Image Outpainting Empowered by Multimodal Large Language Model](https://mlsanity.com/paper/2406.01059/) (2024)
- [OPa-Ma: Text Guided Mamba for 360-degree Image Out-painting](https://mlsanity.com/paper/2407.10923/) (2024)
- [M3DDM+: An improved video outpainting by a modified masking strategy](https://mlsanity.com/paper/2601.11048/) (2026)

## Abstract (arXiv)

Although the inherently ambiguous task of predicting what resides beyond all four edges of an image has rarely been explored before, we demonstrate that GANs hold powerful potential in producing reasonable extrapolations. Two outpainting methods are proposed that aim to instigate this line of research: the first approach uses a context encoder inspired by common inpainting architectures and paradigms, while the second approach adds an extra post-processing step using a single-image generative model. 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.