# Pluralistic Image Completion

arXiv: https://arxiv.org/abs/1903.04227 · HTML: https://mlsanity.com/paper/1903.04227/

## Key facts

- Cited by 162 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Mar 2019.

## Built on by (most cited first, 30 of 162)

- [RePaint: Inpainting using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2201.09865/) (2022)
- [Palette: Image-to-Image Diffusion Models](https://mlsanity.com/paper/2111.05826/) (2021)
- [Resolution-robust Large Mask Inpainting with Fourier Convolutions](https://mlsanity.com/paper/2109.07161/) (2021)
- [TextDiffuser: Diffusion Models as Text Painters](https://mlsanity.com/paper/2305.10855/) (2023)
- [Large Scale Image Completion via Co-Modulated Generative Adversarial Networks](https://mlsanity.com/paper/2103.10428/) (2021)
- [MAT: Mask-Aware Transformer for Large Hole Image Inpainting](https://mlsanity.com/paper/2203.15270/) (2022)
- [BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion](https://mlsanity.com/paper/2403.06976/) (2024)
- [SPIn-NeRF: Multiview Segmentation and Perceptual Inpainting with Neural Radiance Fields](https://mlsanity.com/paper/2211.12254/) (2022)
- [High-Fidelity Pluralistic Image Completion with Transformers](https://mlsanity.com/paper/2103.14031/) (2021)
- [Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAE](https://mlsanity.com/paper/2103.10022/) (2021)
- [Variational Relational Point Completion Network](https://mlsanity.com/paper/2104.10154/) (2021)
- [Diverse Image Inpainting with Bidirectional and Autoregressive Transformers](https://mlsanity.com/paper/2104.12335/) (2021)
- [PD-GAN: Probabilistic Diverse GAN for Image Inpainting](https://mlsanity.com/paper/2105.02201/) (2021)
- [Monte Carlo guided Diffusion for Bayesian linear inverse problems](https://mlsanity.com/paper/2308.07983/) (2023)
- [Towards Coherent Image Inpainting Using Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2304.03322/) (2023)
- [RealFill: Reference-Driven Generation for Authentic Image Completion](https://mlsanity.com/paper/2309.16668/) (2023)
- [Amodal3R: Amodal 3D Reconstruction from Occluded 2D Images](https://mlsanity.com/paper/2503.13439/) (2025)
- [PanoDiffusion: 360-degree Panorama Outpainting via Diffusion](https://mlsanity.com/paper/2307.03177/) (2023)
- [TransFill: Reference-guided Image Inpainting by Merging Multiple Color and Spatial Transformations](https://mlsanity.com/paper/2103.15982/) (2021)
- [Diverse Plausible 360-Degree Image Outpainting for Efficient 3DCG Background Creation](https://mlsanity.com/paper/2203.14668/) (2022)
- [Deep Learning-based Image and Video Inpainting: A Survey](https://mlsanity.com/paper/2401.03395/) (2024)
- [Bridging Global Context Interactions for High-Fidelity Image Completion](https://mlsanity.com/paper/2104.00845/) (2021)
- [Reference-guided Controllable Inpainting of Neural Radiance Fields](https://mlsanity.com/paper/2304.09677/) (2023)
- [Structure Matters: Tackling the Semantic Discrepancy in Diffusion Models for Image Inpainting](https://mlsanity.com/paper/2403.19898/) (2024)
- [Reduce Information Loss in Transformers for Pluralistic Image Inpainting](https://mlsanity.com/paper/2205.05076/) (2022)
- [Image Inpainting by End-to-End Cascaded Refinement with Mask Awareness](https://mlsanity.com/paper/2104.13743/) (2021)
- [BrushEdit: All-In-One Image Inpainting and Editing](https://mlsanity.com/paper/2412.10316/) (2024)
- [Sem2NeRF: Converting Single-View Semantic Masks to Neural Radiance Fields](https://mlsanity.com/paper/2203.10821/) (2022)
- [Learning to Generate Realistic Noisy Images via Pixel-level Noise-aware Adversarial Training](https://mlsanity.com/paper/2204.02844/) (2022)
- [BIPS: Bi-modal Indoor Panorama Synthesis via Residual Depth-aided Adversarial Learning](https://mlsanity.com/paper/2112.06179/) (2021)

## Abstract (arXiv)

Most image completion methods produce only one result for each masked input, although there may be many reasonable possibilities. In this paper, we present an approach for pluralistic image completion -- the task of generating multiple and diverse plausible solutions for image completion. A major challenge faced by learning-based approaches is that usually only one ground truth training instance per label. As such, sampling from conditional VAEs still leads to minimal diversity. To overcome this, we propose a novel and probabilistically principled framework with two parallel paths. One is a reconstructive path that utilizes the only one given ground truth to get prior distribution of missing parts and rebuild the original image from this distribution. The other is a generative path for which the conditional prior is coupled to the distribution obtained in the reconstructive path. Both are supported by GANs. We also introduce a new short+long term attention layer that exploits distant relations among decoder and encoder features, improving appearance consistency. When tested on datasets with buildings (Paris), faces (CelebA-HQ), and natural images (ImageNet), our method not only generated higher-quality completion results, but also with multiple and diverse plausible outputs.