# Diffusion-based image inpainting with internal learning

arXiv: https://arxiv.org/abs/2406.04206 · HTML: https://mlsanity.com/paper/2406.04206/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models.
- Builds on 11 of its 18 references that are in the map.
- First posted on arXiv 6 Jun 2024.

## Placed in

- Diffusion models / [3D, point cloud and scene generation](https://mlsanity.com/diffusion/3d-point-cloud-and-scene-generation/)

## Builds on (most cited first, 11 of 11)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [RePaint: Inpainting using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2201.09865/) (2022)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [Palette: Image-to-Image Diffusion Models](https://mlsanity.com/paper/2111.05826/) (2021)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Resolution-robust Large Mask Inpainting with Fourier Convolutions](https://mlsanity.com/paper/2109.07161/) (2021)
- [Generative Image Inpainting with Contextual Attention](https://mlsanity.com/paper/1801.07892/) (2018)
- [SinGAN: Learning a Generative Model from a Single Natural Image](https://mlsanity.com/paper/1905.01164/) (2019)
- [Single-Image SVBRDF Capture with a Rendering-Aware Deep Network](https://mlsanity.com/paper/1810.09718/) (2018)
- [Towards Universal Texture Synthesis by Combining Texton Broadcasting with Noise Injection in StyleGAN-2](https://mlsanity.com/paper/2203.04221/) (2022)
- [Internal Diverse Image Completion](https://mlsanity.com/paper/2212.10280/) (2022)

## Built on by (most cited first, 1 of 1)

- [Reconstructing Quantum Dot Charge Stability Diagrams with Diffusion Models](https://mlsanity.com/paper/2603.26432/) (2026)

## Abstract (arXiv)

Diffusion models are now the undisputed state-of-the-art for image generation and image restoration. However, they require large amounts of computational power for training and inference. In this paper, we propose lightweight diffusion models for image inpainting that can be trained on a single image, or a few images. We show that our approach competes with large state-of-the-art models in specific cases. We also show that training a model on a single image is particularly relevant for image acquisition modality that differ from the RGB images of standard learning databases. We show results in three different contexts: texture images, line drawing images, and materials BRDF, for which we achieve state-of-the-art results in terms of realism, with a computational load that is greatly reduced compared to concurrent methods.